diff options
91 files changed, 3163 insertions, 922 deletions
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 0e2a152c3aa..c26200b40a4 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -128,7 +128,7 @@ quiet_cmd_bootas = BOOTAS $@ cmd_bootas = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $< quiet_cmd_bootar = BOOTAR $@ - cmd_bootar = $(CROSS32AR) -cr $@.$$$$ $(filter-out FORCE,$^); mv $@.$$$$ $@ + cmd_bootar = $(CROSS32AR) -cr$(KBUILD_ARFLAGS) $@.$$$$ $(filter-out FORCE,$^); mv $@.$$$$ $@ $(obj-libfdt): $(obj)/%.o: $(srctree)/scripts/dtc/libfdt/%.c FORCE $(call if_changed_dep,bootcc) diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index dfa29cb0f47..c74531af72c 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -258,7 +258,7 @@ if [ -z "$cacheit" -o ! -f "$vmz$gzip" -o "$vmz$gzip" -ot "$kernel" ]; then ${CROSS}objcopy $objflags "$kernel" "$vmz.$$" if [ -n "$gzip" ]; then - gzip -f -9 "$vmz.$$" + gzip -n -f -9 "$vmz.$$" fi if [ -n "$cacheit" ]; then @@ -343,7 +343,7 @@ coff) $objbin/hack-coff "$ofile" ;; cuboot*) - gzip -f -9 "$ofile" + gzip -n -f -9 "$ofile" ${MKIMAGE} -A ppc -O linux -T kernel -C gzip -a "$base" -e "$entry" \ $uboot_version -d "$ofile".gz "$ofile" ;; @@ -390,6 +390,6 @@ ps3) odir="$(dirname "$ofile.bin")" rm -f "$odir/otheros.bld" - gzip --force -9 --stdout "$ofile.bin" > "$odir/otheros.bld" + gzip -n --force -9 --stdout "$ofile.bin" > "$odir/otheros.bld" ;; esac diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 249ddd0a27c..7de13865508 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -146,12 +146,18 @@ CONFIG_SCSI_MULTI_LUN=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y CONFIG_SCSI_SAS_ATTRS=m +CONFIG_SCSI_CXGB3_ISCSI=m +CONFIG_SCSI_CXGB4_ISCSI=m +CONFIG_SCSI_BNX2_ISCSI=m +CONFIG_SCSI_BNX2_ISCSI=m +CONFIG_BE2ISCSI=m CONFIG_SCSI_IBMVSCSI=y CONFIG_SCSI_IBMVFC=m CONFIG_SCSI_SYM53C8XX_2=y CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0 CONFIG_SCSI_IPR=y CONFIG_SCSI_QLA_FC=m +CONFIG_SCSI_QLA_ISCSI=m CONFIG_SCSI_LPFC=m CONFIG_ATA=y # CONFIG_ATA_SFF is not set @@ -197,6 +203,8 @@ CONFIG_S2IO=m CONFIG_MYRI10GE=m CONFIG_NETXEN_NIC=m CONFIG_MLX4_EN=m +CONFIG_QLGE=m +CONFIG_BE2NET=m CONFIG_PPP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h index 0893ab9343a..9c70d0ca96d 100644 --- a/arch/powerpc/include/asm/dbell.h +++ b/arch/powerpc/include/asm/dbell.h @@ -27,9 +27,8 @@ enum ppc_dbell { PPC_G_DBELL_MC = 4, /* guest mcheck doorbell */ }; -extern void doorbell_message_pass(int target, int msg); +extern void doorbell_cause_ipi(int cpu, unsigned long data); extern void doorbell_exception(struct pt_regs *regs); -extern void doorbell_check_self(void); extern void doorbell_setup_this_cpu(void); static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag) diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 2f365f5007a..45698d55cd6 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -2,6 +2,8 @@ #define _ASM_POWERPC_IO_H #ifdef __KERNEL__ +#define ARCH_HAS_IOREMAP_WC + /* * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -622,12 +624,13 @@ static inline void iosync(void) * * ioremap is the standard one and provides non-cacheable guarded mappings * and can be hooked by the platform via ppc_md * - * * ioremap_flags allows to specify the page flags as an argument and can - * also be hooked by the platform via ppc_md. ioremap_prot is the exact - * same thing as ioremap_flags. + * * ioremap_prot allows to specify the page flags as an argument and can + * also be hooked by the platform via ppc_md. * * * ioremap_nocache is identical to ioremap * + * * ioremap_wc enables write combining + * * * iounmap undoes such a mapping and can be hooked * * * __ioremap_at (and the pending __iounmap_at) are low level functions to @@ -635,7 +638,7 @@ static inline void iosync(void) * currently be hooked. Must be page aligned. * * * __ioremap is the low level implementation used by ioremap and - * ioremap_flags and cannot be hooked (but can be used by a hook on one + * ioremap_prot and cannot be hooked (but can be used by a hook on one * of the previous ones) * * * __ioremap_caller is the same as above but takes an explicit caller @@ -646,10 +649,10 @@ static inline void iosync(void) * */ extern void __iomem *ioremap(phys_addr_t address, unsigned long size); -extern void __iomem *ioremap_flags(phys_addr_t address, unsigned long size, - unsigned long flags); +extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size, + unsigned long flags); +extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size); #define ioremap_nocache(addr, size) ioremap((addr), (size)) -#define ioremap_prot(addr, size, prot) ioremap_flags((addr), (size), (prot)) extern void iounmap(volatile void __iomem *addr); diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index e1983d57768..1bff591f7f7 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -88,9 +88,6 @@ struct irq_host_ops { /* Dispose of such a mapping */ void (*unmap)(struct irq_host *h, unsigned int virq); - /* Update of such a mapping */ - void (*remap)(struct irq_host *h, unsigned int virq, irq_hw_number_t hw); - /* Translate device-tree interrupt specifier from raw format coming * from the firmware to a irq_hw_number_t (interrupt line number) and * type (sense) that can be passed to set_irq_type(). In the absence @@ -131,7 +128,7 @@ struct irq_host { struct irq_data; extern irq_hw_number_t irqd_to_hwirq(struct irq_data *d); extern irq_hw_number_t virq_to_hw(unsigned int virq); -extern struct irq_host *virq_to_host(unsigned int virq); +extern bool virq_is_host(unsigned int virq, struct irq_host *host); /** * irq_alloc_host - Allocate a new irq_host data structure diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index a077adc0b35..e0298d26ce5 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -210,6 +210,8 @@ struct dtl_entry { #define DISPATCH_LOG_BYTES 4096 /* bytes per cpu */ #define N_DISPATCH_LOG (DISPATCH_LOG_BYTES / sizeof(struct dtl_entry)) +extern struct kmem_cache *dtl_cache; + /* * When CONFIG_VIRT_CPU_ACCOUNTING = y, the cpu accounting code controls * reading from the dispatch trace log. If other code wants to consume diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index c6345acf166..47cacddb14c 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -29,21 +29,6 @@ struct file; struct pci_controller; struct kimage; -#ifdef CONFIG_SMP -struct smp_ops_t { - void (*message_pass)(int target, int msg); - int (*probe)(void); - int (*kick_cpu)(int nr); - void (*setup_cpu)(int nr); - void (*bringup_done)(void); - void (*take_timebase)(void); - void (*give_timebase)(void); - int (*cpu_disable)(void); - void (*cpu_die)(unsigned int nr); - int (*cpu_bootable)(unsigned int nr); -}; -#endif - struct machdep_calls { char *name; #ifdef CONFIG_PPC64 @@ -312,12 +297,6 @@ extern sys_ctrler_t sys_ctrler; #endif /* CONFIG_PPC_PMAC */ -#ifdef CONFIG_SMP -/* Poor default implementations */ -extern void __devinit smp_generic_give_timebase(void); -extern void __devinit smp_generic_take_timebase(void); -#endif /* CONFIG_SMP */ - /* Functions to produce codes on the leds. * The SRC code should be unique for the message category and should diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h index 488c52eb64c..9356262fd3c 100644 --- a/arch/powerpc/include/asm/page_64.h +++ b/arch/powerpc/include/asm/page_64.h @@ -59,24 +59,7 @@ static __inline__ void clear_page(void *addr) : "ctr", "memory"); } -extern void copy_4K_page(void *to, void *from); - -#ifdef CONFIG_PPC_64K_PAGES -static inline void copy_page(void *to, void *from) -{ - unsigned int i; - for (i=0; i < (1 << (PAGE_SHIFT - 12)); i++) { - copy_4K_page(to, from); - to += 4096; - from += 4096; - } -} -#else /* CONFIG_PPC_64K_PAGES */ -static inline void copy_page(void *to, void *from) -{ - copy_4K_page(to, from); -} -#endif /* CONFIG_PPC_64K_PAGES */ +extern void copy_page(void *to, void *from); /* Log 2 of page table size */ extern u64 ppc64_pft_size; diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index 2b09cd522d3..81576ee0cfb 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -257,21 +257,20 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - unsigned long old; - if ((pte_val(*ptep) & _PAGE_RW) == 0) - return; - old = pte_update(mm, addr, ptep, _PAGE_RW, 0); + if ((pte_val(*ptep) & _PAGE_RW) == 0) + return; + + pte_update(mm, addr, ptep, _PAGE_RW, 0); } static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - unsigned long old; - if ((pte_val(*ptep) & _PAGE_RW) == 0) return; - old = pte_update(mm, addr, ptep, _PAGE_RW, 1); + + pte_update(mm, addr, ptep, _PAGE_RW, 1); } /* diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index fdec5933305..c5cae0dd176 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -824,6 +824,11 @@ FTR_SECTION_ELSE_NESTED(66); \ mtspr SPRN_SPRG_HSCRATCH0,rX; \ ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_HVMODE_206, 66) + +#else /* CONFIG_PPC_BOOK3S_64 */ +#define GET_SCRATCH0(rX) mfspr rX,SPRN_SPRG_SCRATCH0 +#define SET_SCRATCH0(rX) mtspr SPRN_SPRG_SCRATCH0,rX + #endif #ifdef CONFIG_PPC_BOOK3E_64 diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 50873493a97..880b8c1e6e5 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -20,6 +20,7 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/kernel.h> +#include <linux/irqreturn.h> #ifndef __ASSEMBLY__ @@ -35,9 +36,26 @@ extern void cpu_die(void); #ifdef CONFIG_SMP -extern void smp_send_debugger_break(int cpu); -extern void smp_message_recv(int); +struct smp_ops_t { + void (*message_pass)(int cpu, int msg); +#ifdef CONFIG_PPC_SMP_MUXED_IPI + void (*cause_ipi)(int cpu, unsigned long data); +#endif + int (*probe)(void); + int (*kick_cpu)(int nr); + void (*setup_cpu)(int nr); + void (*bringup_done)(void); + void (*take_timebase)(void); + void (*give_timebase)(void); + int (*cpu_disable)(void); + void (*cpu_die)(unsigned int nr); + int (*cpu_bootable)(unsigned int nr); +}; + +extern void smp_send_debugger_break(void); extern void start_secondary_resume(void); +extern void __devinit smp_generic_give_timebase(void); +extern void __devinit smp_generic_take_timebase(void); DECLARE_PER_CPU(unsigned int, cpu_pvr); @@ -94,13 +112,16 @@ extern int cpu_to_core_id(int cpu); #define PPC_MSG_CALL_FUNC_SINGLE 2 #define PPC_MSG_DEBUGGER_BREAK 3 -/* - * irq controllers that have dedicated ipis per message and don't - * need additional code in the action handler may use this - */ +/* for irq controllers that have dedicated ipis per message (4) */ extern int smp_request_message_ipi(int virq, int message); extern const char *smp_ipi_name[]; +/* for irq controllers with only a single ipi */ +extern void smp_muxed_ipi_set_data(int cpu, unsigned long data); +extern void smp_muxed_ipi_message_pass(int cpu, int msg); +extern void smp_muxed_ipi_resend(void); +extern irqreturn_t smp_ipi_demux(void); + void smp_init_iSeries(void); void smp_init_pSeries(void); void smp_init_cell(void); @@ -170,6 +191,8 @@ extern unsigned long __secondary_hold_spinloop; extern unsigned long __secondary_hold_acknowledge; extern char __secondary_hold; +extern irqreturn_t debug_ipi_action(int irq, void *data); + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h index 5e474ddd227..2dc595dda03 100644 --- a/arch/powerpc/include/asm/system.h +++ b/arch/powerpc/include/asm/system.h @@ -219,8 +219,6 @@ extern int mem_init_done; /* set on boot once kmalloc can be called */ extern int init_bootmem_done; /* set once bootmem is available */ extern phys_addr_t memory_limit; extern unsigned long klimit; - -extern void *alloc_maybe_bootmem(size_t size, gfp_t mask); extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); extern int powersave_nap; /* set if nap mode can be used in idle loop */ diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index 6c06306c410..b183a406201 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -40,7 +40,7 @@ struct icp_ops { void (*teardown_cpu)(void); void (*flush_ipi)(void); #ifdef CONFIG_SMP - void (*message_pass)(int target, int msg); + void (*cause_ipi)(int cpu, unsigned long data); irq_handler_t ipi_action; #endif }; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 82e0bed0650..9aab3631257 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -78,7 +78,6 @@ obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o dbell.o obj-$(CONFIG_PPC_BOOK3E_64) += dbell.o extra-y := head_$(CONFIG_WORD_SIZE).o -extra-$(CONFIG_PPC_BOOK3E_32) := head_new_booke.o extra-$(CONFIG_40x) := head_40x.o extra-$(CONFIG_44x) := head_44x.o extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 21f2c781ded..4e6ee944495 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -236,7 +236,7 @@ static void crash_kexec_wait_realmode(int cpu) int i; msecs = 10000; - for (i=0; i < NR_CPUS && msecs > 0; i++) { + for (i=0; i < nr_cpu_ids && msecs > 0; i++) { if (i == cpu) continue; diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index 3307a52d797..2cc451aaaca 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -13,84 +13,35 @@ #include <linux/kernel.h> #include <linux/smp.h> #include <linux/threads.h> -#include <linux/percpu.h> +#include <linux/hardirq.h> #include <asm/dbell.h> #include <asm/irq_regs.h> #ifdef CONFIG_SMP -struct doorbell_cpu_info { - unsigned long messages; /* current messages bits */ - unsigned int tag; /* tag value */ -}; - -static DEFINE_PER_CPU(struct doorbell_cpu_info, doorbell_cpu_info); - void doorbell_setup_this_cpu(void) { - struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info); + unsigned long tag = mfspr(SPRN_PIR) & 0x3fff; - info->messages = 0; - info->tag = mfspr(SPRN_PIR) & 0x3fff; + smp_muxed_ipi_set_data(smp_processor_id(), tag); } -void doorbell_message_pass(int target, int msg) +void doorbell_cause_ipi(int cpu, unsigned long data) { - struct doorbell_cpu_info *info; - int i; - - if (target < NR_CPUS) { - info = &per_cpu(doorbell_cpu_info, target); - set_bit(msg, &info->messages); - ppc_msgsnd(PPC_DBELL, 0, info->tag); - } - else if (target == MSG_ALL_BUT_SELF) { - for_each_online_cpu(i) { - if (i == smp_processor_id()) - continue; - info = &per_cpu(doorbell_cpu_info, i); - set_bit(msg, &info->messages); - ppc_msgsnd(PPC_DBELL, 0, info->tag); - } - } - else { /* target == MSG_ALL */ - for_each_online_cpu(i) { - info = &per_cpu(doorbell_cpu_info, i); - set_bit(msg, &info->messages); - } - ppc_msgsnd(PPC_DBELL, PPC_DBELL_MSG_BRDCAST, 0); - } + ppc_msgsnd(PPC_DBELL, 0, data); } void doorbell_exception(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info); - int msg; - /* Warning: regs can be NULL when called from irq enable */ + irq_enter(); - if (!info->messages || (num_online_cpus() < 2)) - goto out; + smp_ipi_demux(); - for (msg = 0; msg < 4; msg++) - if (test_and_clear_bit(msg, &info->messages)) - smp_message_recv(msg); - -out: + irq_exit(); set_irq_regs(old_regs); } - -void doorbell_check_self(void) -{ - struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info); - - if (!info->messages) - return; - - ppc_msgsnd(PPC_DBELL, 0, info->tag); -} - #else /* CONFIG_SMP */ void doorbell_exception(struct pt_regs *regs) { diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 0ec3b42717d..a85f4874cba 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -211,11 +211,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) mr r9,r13 GET_PACA(r13) mfspr r11,SPRN_SRR0 - ld r12,PACAKBASE(r13) - ld r10,PACAKMSR(r13) - LOAD_HANDLER(r12, system_call_entry) - mtspr SPRN_SRR0,r12 mfspr r12,SPRN_SRR1 + ld r10,PACAKBASE(r13) + LOAD_HANDLER(r10, system_call_entry) + mtspr SPRN_SRR0,r10 + ld r10,PACAKMSR(r13) mtspr SPRN_SRR1,r10 rfid b . /* prevent speculative execution */ diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 98c4b29a56f..ba250d505e0 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -805,19 +805,6 @@ _ENTRY(copy_and_flush) blr #ifdef CONFIG_SMP -#ifdef CONFIG_GEMINI - .globl __secondary_start_gemini -__secondary_start_gemini: - mfspr r4,SPRN_HID0 - ori r4,r4,HID0_ICFI - li r3,0 - ori r3,r3,HID0_ICE - andc r4,r4,r3 - mtspr SPRN_HID0,r4 - sync - b __secondary_start -#endif /* CONFIG_GEMINI */ - .globl __secondary_start_mpc86xx __secondary_start_mpc86xx: mfspr r3, SPRN_PIR diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 73d6e9afcdf..ba504099844 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -218,13 +218,19 @@ generic_secondary_common_init: */ LOAD_REG_ADDR(r13, paca) /* Load paca pointer */ ld r13,0(r13) /* Get base vaddr of paca array */ +#ifndef CONFIG_SMP + addi r13,r13,PACA_SIZE /* know r13 if used accidentally */ + b .kexec_wait /* wait for next kernel if !SMP */ +#else + LOAD_REG_ADDR(r7, nr_cpu_ids) /* Load nr_cpu_ids address */ + lwz r7,0(r7) /* also the max paca allocated */ li r5,0 /* logical cpu id */ 1: lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ cmpw r6,r24 /* Compare to our id */ beq 2f addi r13,r13,PACA_SIZE /* Loop to next PACA on miss */ addi r5,r5,1 - cmpwi r5,NR_CPUS + cmpw r5,r7 /* Check if more pacas exist */ blt 1b mr r3,r24 /* not found, copy phys to r3 */ @@ -259,9 +265,6 @@ generic_secondary_common_init: 4: HMT_LOW lbz r23,PACAPROCSTART(r13) /* Test if this processor should */ /* start. */ -#ifndef CONFIG_SMP - b 4b /* Never go on non-SMP */ -#else cmpwi 0,r23,0 beq 4b /* Loop until told to go */ @@ -273,7 +276,7 @@ generic_secondary_common_init: subi r1,r1,STACK_FRAME_OVERHEAD b __secondary_start -#endif +#endif /* SMP */ /* * Turn the MMU off. diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index a81dd74414b..a24d37d4cf5 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -66,7 +66,6 @@ #include <asm/ptrace.h> #include <asm/machdep.h> #include <asm/udbg.h> -#include <asm/dbell.h> #include <asm/smp.h> #ifdef CONFIG_PPC64 @@ -160,7 +159,8 @@ notrace void arch_local_irq_restore(unsigned long en) #if defined(CONFIG_BOOKE) && defined(CONFIG_SMP) /* Check for pending doorbell interrupts and resend to ourself */ - doorbell_check_self(); + if (cpu_has_feature(CPU_FTR_DBELL)) + smp_muxed_ipi_resend(); #endif /* @@ -493,7 +493,6 @@ struct irq_map_entry { static LIST_HEAD(irq_hosts); static DEFINE_RAW_SPINLOCK(irq_big_lock); -static unsigned int revmap_trees_allocated; static DEFINE_MUTEX(revmap_trees_mutex); static struct irq_map_entry irq_map[NR_IRQS]; static unsigned int irq_virq_count = NR_IRQS; @@ -511,11 +510,11 @@ irq_hw_number_t virq_to_hw(unsigned int virq) } EXPORT_SYMBOL_GPL(virq_to_hw); -struct irq_host *virq_to_host(unsigned int virq) +bool virq_is_host(unsigned int virq, struct irq_host *host) { - return irq_map[virq].host; + return irq_map[virq].host == host; } -EXPORT_SYMBOL_GPL(virq_to_host); +EXPORT_SYMBOL_GPL(virq_is_host); static int default_irq_host_match(struct irq_host *h, struct device_node *np) { @@ -537,7 +536,7 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, /* Allocate structure and revmap table if using linear mapping */ if (revmap_type == IRQ_HOST_MAP_LINEAR) size += revmap_arg * sizeof(unsigned int); - host = zalloc_maybe_bootmem(size, GFP_KERNEL); + host = kzalloc(size, GFP_KERNEL); if (host == NULL) return NULL; @@ -587,14 +586,14 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, irq_map[i].host = host; smp_wmb(); - /* Clear norequest flags */ - irq_clear_status_flags(i, IRQ_NOREQUEST); - /* Legacy flags are left to default at this point, * one can then use irq_create_mapping() to * explicitly change them */ ops->map(host, i, i); + + /* Clear norequest flags */ + irq_clear_status_flags(i, IRQ_NOREQUEST); } break; case IRQ_HOST_MAP_LINEAR: @@ -605,6 +604,9 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, smp_wmb(); host->revmap_data.linear.revmap = rmap; break; + case IRQ_HOST_MAP_TREE: + INIT_RADIX_TREE(&host->revmap_data.tree, GFP_KERNEL); + break; default: break; } @@ -662,8 +664,6 @@ static int irq_setup_virq(struct irq_host *host, unsigned int virq, goto error; } - irq_clear_status_flags(virq, IRQ_NOREQUEST); - /* map it */ smp_wmb(); irq_map[virq].hwirq = hwirq; @@ -674,6 +674,8 @@ static int irq_setup_virq(struct irq_host *host, unsigned int virq, goto errdesc; } + irq_clear_status_flags(virq, IRQ_NOREQUEST); + return 0; errdesc: @@ -730,8 +732,6 @@ unsigned int irq_create_mapping(struct irq_host *host, */ virq = irq_find_mapping(host, hwirq); if (virq != NO_IRQ) { - if (host->ops->remap) - host->ops->remap(host, virq, hwirq); pr_debug("irq: -> existing mapping on virq %d\n", virq); return virq; } @@ -812,14 +812,15 @@ void irq_dispose_mapping(unsigned int virq) return; host = irq_map[virq].host; - WARN_ON (host == NULL); - if (host == NULL) + if (WARN_ON(host == NULL)) return; /* Never unmap legacy interrupts */ if (host->revmap_type == IRQ_HOST_MAP_LEGACY) return; + irq_set_status_flags(virq, IRQ_NOREQUEST); + /* remove chip and handler */ irq_set_chip_and_handler(virq, NULL, NULL); @@ -839,13 +840,6 @@ void irq_dispose_mapping(unsigned int virq) host->revmap_data.linear.revmap[hwirq] = NO_IRQ; break; case IRQ_HOST_MAP_TREE: - /* - * Check if radix tree allocated yet, if not then nothing to - * remove. - */ - smp_rmb(); - if (revmap_trees_allocated < 1) - break; mutex_lock(&revmap_trees_mutex); radix_tree_delete(&host->revmap_data.tree, hwirq); mutex_unlock(&revmap_trees_mutex); @@ -856,8 +850,6 @@ void irq_dispose_mapping(unsigned int virq) smp_mb(); irq_map[virq].hwirq = host->inval_irq; - irq_set_status_flags(virq, IRQ_NOREQUEST); - irq_free_descs(virq, 1); /* Free it */ irq_free_virt(virq, 1); @@ -903,16 +895,9 @@ unsigned int irq_radix_revmap_lookup(struct irq_host *host, struct irq_map_entry *ptr; unsigned int virq; - WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE); - - /* - * Check if the radix tree exists and has bee initialized. - * If not, we fallback to slow mode - */ - if (revmap_trees_allocated < 2) + if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_TREE)) return irq_find_mapping(host, hwirq); - /* Now try to resolve */ /* * No rcu_read_lock(ing) needed, the ptr returned can't go under us * as it's referencing an entry in the static irq_map table. @@ -935,16 +920,7 @@ unsigned int irq_radix_revmap_lookup(struct irq_host *host, void irq_radix_revmap_insert(struct irq_host *host, unsigned int virq, irq_hw_number_t hwirq) { - - WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE); - - /* - * Check if the radix tree exists yet. - * If not, then the irq will be inserted into the tree when it gets - * initialized. - */ - smp_rmb(); - if (revmap_trees_allocated < 1) + if (WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE)) return; if (virq != NO_IRQ) { @@ -960,7 +936,8 @@ unsigned int irq_linear_revmap(struct irq_host *host, { unsigned int *revmap; - WARN_ON(host->revmap_type != IRQ_HOST_MAP_LINEAR); + if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_LINEAR)) + return irq_find_mapping(host, hwirq); /* Check revmap bounds */ if (unlikely(hwirq >= host->revmap_data.linear.size)) @@ -1054,53 +1031,6 @@ int arch_early_irq_init(void) return 0; } -/* We need to create the radix trees late */ -static int irq_late_init(void) -{ - struct irq_host *h; - unsigned int i; - - /* - * No mutual exclusion with respect to accessors of the tree is needed - * here as the synchronization is done via the state variable - * revmap_trees_allocated. - */ - list_for_each_entry(h, &irq_hosts, link) { - if (h->revmap_type == IRQ_HOST_MAP_TREE) - INIT_RADIX_TREE(&h->revmap_data.tree, GFP_KERNEL); - } - - /* - * Make sure the radix trees inits are visible before setting - * the flag - */ - smp_wmb(); - revmap_trees_allocated = 1; - - /* - * Insert the reverse mapping for those interrupts already present - * in irq_map[]. - */ - mutex_lock(&revmap_trees_mutex); - for (i = 0; i < irq_virq_count; i++) { - if (irq_map[i].host && - (irq_map[i].host->revmap_type == IRQ_HOST_MAP_TREE)) - radix_tree_insert(&irq_map[i].host->revmap_data.tree, - irq_map[i].hwirq, &irq_map[i]); - } - mutex_unlock(&revmap_trees_mutex); - - /* - * Make sure the radix trees insertions are visible before setting - * the flag - */ - smp_wmb(); - revmap_trees_allocated = 2; - - return 0; -} -arch_initcall(irq_late_init); - #ifdef CONFIG_VIRQ_DEBUG static int virq_debug_show(struct seq_file *m, void *private) { diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 42850ee00ad..bd9d35f59cf 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -109,7 +109,7 @@ static int kgdb_call_nmi_hook(struct pt_regs *regs) #ifdef CONFIG_SMP void kgdb_roundup_cpus(unsigned long flags) { - smp_send_debugger_break(MSG_ALL_BUT_SELF); + smp_send_debugger_break(); } #endif diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 206a321a71d..e89df59cdc5 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -462,7 +462,8 @@ _GLOBAL(disable_kernel_fp) * wait for the flag to change, indicating this kernel is going away but * the slave code for the next one is at addresses 0 to 100. * - * This is used by all slaves. + * This is used by all slaves, even those that did not find a matching + * paca in the secondary startup code. * * Physical (hardware) cpu id should be in r3. */ @@ -471,10 +472,6 @@ _GLOBAL(kexec_wait) 1: mflr r5 addi r5,r5,kexec_flag-1b - li r4,KEXEC_STATE_REAL_MODE - stb r4,PACAKEXECSTATE(r13) - SYNC - 99: HMT_LOW #ifdef CONFIG_KEXEC /* use no memory without kexec */ lwz r4,0(r5) @@ -499,11 +496,17 @@ kexec_flag: * * get phys id from paca * switch to real mode + * mark the paca as no longer used * join other cpus in kexec_wait(phys_id) */ _GLOBAL(kexec_smp_wait) lhz r3,PACAHWCPUID(r13) bl real_mode + + li r4,KEXEC_STATE_REAL_MODE + stb r4,PACAKEXECSTATE(r13) + SYNC + b .kexec_wait /* diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 102244edecf..efeb8818418 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -7,7 +7,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/threads.h> +#include <linux/smp.h> #include <linux/module.h> #include <linux/memblock.h> @@ -178,7 +178,7 @@ static int __initdata paca_size; void __init allocate_pacas(void) { - int nr_cpus, cpu, limit; + int cpu, limit; /* * We can't take SLB misses on the paca, and we want to access them @@ -190,23 +190,18 @@ void __init allocate_pacas(void) if (firmware_has_feature(FW_FEATURE_ISERIES)) limit = min(limit, HvPagesToMap * HVPAGESIZE); - nr_cpus = NR_CPUS; - /* On iSeries we know we can never have more than 64 cpus */ - if (firmware_has_feature(FW_FEATURE_ISERIES)) - nr_cpus = min(64, nr_cpus); - - paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpus); + paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids); paca = __va(memblock_alloc_base(paca_size, PAGE_SIZE, limit)); memset(paca, 0, paca_size); printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n", - paca_size, nr_cpus, paca); + paca_size, nr_cpu_ids, paca); - allocate_lppacas(nr_cpus, limit); + allocate_lppacas(nr_cpu_ids, limit); /* Can't use for_each_*_cpu, as they aren't functional yet */ - for (cpu = 0; cpu < nr_cpus; cpu++) + for (cpu = 0; cpu < nr_cpu_ids; cpu++) initialise_paca(&paca[cpu], cpu); } diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index d225d99fe39..6baabc13306 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -43,10 +43,9 @@ void * __devinit update_dn_pci_info(struct device_node *dn, void *data) const u32 *regs; struct pci_dn *pdn; - pdn = alloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL); + pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL); if (pdn == NULL) return NULL; - memset(pdn, 0, sizeof(*pdn)); dn->data = pdn; pdn->node = dn; pdn->phb = phb; diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index ef3ef566235..7d28f540200 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -54,7 +54,6 @@ extern void single_step_exception(struct pt_regs *regs); extern int sys_sigreturn(struct pt_regs *regs); EXPORT_SYMBOL(clear_pages); -EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(ISA_DMA_THRESHOLD); EXPORT_SYMBOL(DMA_MODE_READ); EXPORT_SYMBOL(DMA_MODE_WRITE); @@ -88,9 +87,7 @@ EXPORT_SYMBOL(__copy_tofrom_user); EXPORT_SYMBOL(__clear_user); EXPORT_SYMBOL(__strncpy_from_user); EXPORT_SYMBOL(__strnlen_user); -#ifdef CONFIG_PPC64 -EXPORT_SYMBOL(copy_4K_page); -#endif +EXPORT_SYMBOL(copy_page); #if defined(CONFIG_PCI) && defined(CONFIG_PPC32) EXPORT_SYMBOL(isa_io_base); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 5f5e6aed2b7..5311a26dcf4 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -68,6 +68,7 @@ int __initdata iommu_force_on; unsigned long tce_alloc_start, tce_alloc_end; u64 ppc64_rma_size; #endif +static phys_addr_t first_memblock_size; static int __init early_parse_mem(char *p) { @@ -505,11 +506,14 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) size = 0x80000000ul - base; } #endif - - /* First MEMBLOCK added, do some special initializations */ - if (memstart_addr == ~(phys_addr_t)0) - setup_initial_memory_limit(base, size); - memstart_addr = min((u64)memstart_addr, base); + /* Keep track of the beginning of memory -and- the size of + * the very first block in the device-tree as it represents + * the RMA on ppc64 server + */ + if (base < memstart_addr) { + memstart_addr = base; + first_memblock_size = size; + } /* Add the chunk to the MEMBLOCK list */ memblock_add(base, size); @@ -694,6 +698,7 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_root, NULL); of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); + setup_initial_memory_limit(memstart_addr, first_memblock_size); /* Save command line for /proc/cmdline and then parse parameters */ strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 1475df6e403..79fca2651b6 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -404,7 +404,7 @@ static void __init cpu_init_thread_core_maps(int tpc) * cpu_present_mask * * Having the possible map set up early allows us to restrict allocations - * of things like irqstacks to num_possible_cpus() rather than NR_CPUS. + * of things like irqstacks to nr_cpu_ids rather than NR_CPUS. * * We do not initialize the online map here; cpus set their own bits in * cpu_online_mask as they come up. @@ -424,7 +424,7 @@ void __init smp_setup_cpu_maps(void) DBG("smp_setup_cpu_maps()\n"); - while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < NR_CPUS) { + while ((dn = of_find_node_by_type(dn, "cpu")) && cpu < nr_cpu_ids) { const int *intserv; int j, len; @@ -443,7 +443,7 @@ void __init smp_setup_cpu_maps(void) intserv = &cpu; /* assume logical == phys */ } - for (j = 0; j < nthreads && cpu < NR_CPUS; j++) { + for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) { DBG(" thread %d -> cpu %d (hard id %d)\n", j, cpu, intserv[j]); set_cpu_present(cpu, true); @@ -483,12 +483,12 @@ void __init smp_setup_cpu_maps(void) if (cpu_has_feature(CPU_FTR_SMT)) maxcpus *= nthreads; - if (maxcpus > NR_CPUS) { + if (maxcpus > nr_cpu_ids) { printk(KERN_WARNING "Partition configured for %d cpus, " "operating system maximum is %d.\n", - maxcpus, NR_CPUS); - maxcpus = NR_CPUS; + maxcpus, nr_cpu_ids); + maxcpus = nr_cpu_ids; } else printk(KERN_INFO "Partition configured for %d cpus.\n", maxcpus); @@ -510,7 +510,7 @@ void __init smp_setup_cpu_maps(void) cpu_init_thread_core_maps(nthreads); /* Now that possible cpus are set, set nr_cpu_ids for later use */ - nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1; + setup_nr_cpu_ids(); free_unused_pacas(); } @@ -602,6 +602,10 @@ int check_legacy_ioport(unsigned long base_port) * name instead */ if (!np) np = of_find_node_by_name(NULL, "8042"); + if (np) { + of_i8042_kbd_irq = 1; + of_i8042_aux_irq = 12; + } break; case FDC_BASE: /* FDC1 */ np = of_find_node_by_type(NULL, "fdc"); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 0eefccd3316..dd1973fed30 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -111,35 +111,6 @@ int __devinit smp_generic_kick_cpu(int nr) } #endif -void smp_message_recv(int msg) -{ - switch(msg) { - case PPC_MSG_CALL_FUNCTION: - generic_smp_call_function_interrupt(); - break; - case PPC_MSG_RESCHEDULE: - /* we notice need_resched on exit */ - break; - case PPC_MSG_CALL_FUNC_SINGLE: - generic_smp_call_function_single_interrupt(); - break; - case PPC_MSG_DEBUGGER_BREAK: - if (crash_ipi_function_ptr) { - crash_ipi_function_ptr(get_irq_regs()); - break; - } -#ifdef CONFIG_DEBUGGER - debugger_ipi(get_irq_regs()); - break; -#endif /* CONFIG_DEBUGGER */ - /* FALLTHROUGH */ - default: - printk("SMP %d: smp_message_recv(): unknown msg %d\n", - smp_processor_id(), msg); - break; - } -} - static irqreturn_t call_function_action(int irq, void *data) { generic_smp_call_function_interrupt(); @@ -158,9 +129,17 @@ static irqreturn_t call_function_single_action(int irq, void *data) return IRQ_HANDLED; } -static irqreturn_t debug_ipi_action(int irq, void *data) +irqreturn_t debug_ipi_action(int irq, void *data) { - smp_message_recv(PPC_MSG_DEBUGGER_BREAK); + if (crash_ipi_function_ptr) { + crash_ipi_function_ptr(get_irq_regs()); + return IRQ_HANDLED; + } + +#ifdef CONFIG_DEBUGGER + debugger_ipi(get_irq_regs()); +#endif /* CONFIG_DEBUGGER */ + return IRQ_HANDLED; } @@ -199,6 +178,66 @@ int smp_request_message_ipi(int virq, int msg) return err; } +#ifdef CONFIG_PPC_SMP_MUXED_IPI +struct cpu_messages { + int messages; /* current messages */ + unsigned long data; /* data for cause ipi */ +}; +static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_messages, ipi_message); + +void smp_muxed_ipi_set_data(int cpu, unsigned long data) +{ + struct cpu_messages *info = &per_cpu(ipi_message, cpu); + + info->data = data; +} + +void smp_muxed_ipi_message_pass(int cpu, int msg) +{ + struct cpu_messages *info = &per_cpu(ipi_message, cpu); + char *message = (char *)&info->messages; + + message[msg] = 1; + mb(); + smp_ops->cause_ipi(cpu, info->data); +} + +void smp_muxed_ipi_resend(void) +{ + struct cpu_messages *info = &__get_cpu_var(ipi_message); + + if (info->messages) + smp_ops->cause_ipi(smp_processor_id(), info->data); +} + +irqreturn_t smp_ipi_demux(void) +{ + struct cpu_messages *info = &__get_cpu_var(ipi_message); + unsigned int all; + + mb(); /* order any irq clear */ + + do { + all = xchg_local(&info->messages, 0); + +#ifdef __BIG_ENDIAN + if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION))) + generic_smp_call_function_interrupt(); + if (all & (1 << (24 - 8 * PPC_MSG_RESCHEDULE))) + reschedule_action(0, NULL); /* upcoming sched hook */ + if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNC_SINGLE))) + generic_smp_call_function_single_interrupt(); + if (all & (1 << (24 - 8 * PPC_MSG_DEBUGGER_BREAK))) + debug_ipi_action(0, NULL); +#else +#error Unsupported ENDIAN +#endif + } while (info->messages); + + return IRQ_HANDLED; +} +#endif /* CONFIG_PPC_SMP_MUXED_IPI */ + void smp_send_reschedule(int cpu) { if (likely(smp_ops)) @@ -218,11 +257,18 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION); } -#ifdef CONFIG_DEBUGGER -void smp_send_debugger_break(int cpu) +#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) +void smp_send_debugger_break(void) { - if (likely(smp_ops)) - smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK); + int cpu; + int me = raw_smp_processor_id(); + + if (unlikely(!smp_ops)) + return; + + for_each_online_cpu(cpu) + if (cpu != me) + smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK); } #endif @@ -230,9 +276,9 @@ void smp_send_debugger_break(int cpu) void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) { crash_ipi_function_ptr = crash_ipi_callback; - if (crash_ipi_callback && smp_ops) { + if (crash_ipi_callback) { mb(); - smp_ops->message_pass(MSG_ALL_BUT_SELF, PPC_MSG_DEBUGGER_BREAK); + smp_send_debugger_break(); } } #endif diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 9de6f396cf8..4d5a3edff49 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -102,7 +102,7 @@ _GLOBAL(giveup_altivec) MTMSRD(r5) /* enable use of VMX now */ isync PPC_LCMPI 0,r3,0 - beqlr- /* if no previous owner, done */ + beqlr /* if no previous owner, done */ addi r3,r3,THREAD /* want THREAD of task */ PPC_LL r5,PT_REGS(r3) PPC_LCMPI 0,r5,0 diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index c961de40c67..0f95b5cce03 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -236,7 +236,7 @@ void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu) int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu) { - return test_bit(BOOK3S_INTERRUPT_DECREMENTER >> 7, &vcpu->arch.pending_exceptions); + return test_bit(BOOK3S_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions); } void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu) diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index ae99af66ca3..1a1b34487e7 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -112,7 +112,9 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_MACHINE_CHECK INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_DATA_STORAGE INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_INST_STORAGE INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_EXTERNAL +#ifdef CONFIG_PPC_BOOK3S_64 INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_EXTERNAL_HV +#endif INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_ALIGNMENT INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_PROGRAM INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_FP_UNAVAIL diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c index f53e09c7dac..13b676c20d1 100644 --- a/arch/powerpc/lib/alloc.c +++ b/arch/powerpc/lib/alloc.c @@ -6,14 +6,6 @@ #include <asm/system.h> -void * __init_refok alloc_maybe_bootmem(size_t size, gfp_t mask) -{ - if (mem_init_done) - return kmalloc(size, mask); - else - return alloc_bootmem(size); -} - void * __init_refok zalloc_maybe_bootmem(size_t size, gfp_t mask) { void *p; diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index 4d4eeb90048..53dcb6b1b70 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -6,6 +6,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ +#include <asm/page.h> #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/asm-offsets.h> @@ -15,9 +16,9 @@ PPC64_CACHES: .tc ppc64_caches[TC],ppc64_caches .section ".text" - -_GLOBAL(copy_4K_page) - li r5,4096 /* 4K page size */ +_GLOBAL(copy_page) + lis r5,PAGE_SIZE@h + ori r5,r5,PAGE_SIZE@l BEGIN_FTR_SECTION ld r10,PPC64_CACHES@toc(r2) lwz r11,DCACHEL1LOGLINESIZE(r10) /* log2 of cache line size */ diff --git a/arch/powerpc/lib/devres.c b/arch/powerpc/lib/devres.c index deac4d30daf..e91615abae6 100644 --- a/arch/powerpc/lib/devres.c +++ b/arch/powerpc/lib/devres.c @@ -9,11 +9,11 @@ #include <linux/device.h> /* devres_*(), devm_ioremap_release() */ #include <linux/gfp.h> -#include <linux/io.h> /* ioremap_flags() */ +#include <linux/io.h> /* ioremap_prot() */ #include <linux/module.h> /* EXPORT_SYMBOL() */ /** - * devm_ioremap_prot - Managed ioremap_flags() + * devm_ioremap_prot - Managed ioremap_prot() * @dev: Generic device to remap IO address for * @offset: BUS offset to map * @size: Size of map @@ -31,7 +31,7 @@ void __iomem *devm_ioremap_prot(struct device *dev, resource_size_t offset, if (!ptr) return NULL; - addr = ioremap_flags(offset, size, flags); + addr = ioremap_prot(offset, size, flags); if (addr) { *ptr = addr; devres_add(dev, ptr); diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 8dc41c0157f..51f87956f8f 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -133,7 +133,15 @@ ioremap(phys_addr_t addr, unsigned long size) EXPORT_SYMBOL(ioremap); void __iomem * -ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags) +ioremap_wc(phys_addr_t addr, unsigned long size) +{ + return __ioremap_caller(addr, size, _PAGE_NO_CACHE, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_wc); + +void __iomem * +ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags) { /* writeable implies dirty for kernel addresses */ if (flags & _PAGE_RW) @@ -152,7 +160,7 @@ ioremap_flags(phys_addr_t addr, unsigned long size, unsigned long flags) return __ioremap_caller(addr, size, flags, __builtin_return_address(0)); } -EXPORT_SYMBOL(ioremap_flags); +EXPORT_SYMBOL(ioremap_prot); void __iomem * __ioremap(phys_addr_t addr, unsigned long size, unsigned long flags) diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 88927a05cdc..6e595f6496d 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -255,7 +255,17 @@ void __iomem * ioremap(phys_addr_t addr, unsigned long size) return __ioremap_caller(addr, size, flags, caller); } -void __iomem * ioremap_flags(phys_addr_t addr, unsigned long size, +void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size) +{ + unsigned long flags = _PAGE_NO_CACHE; + void *caller = __builtin_return_address(0); + + if (ppc_md.ioremap) + return ppc_md.ioremap(addr, size, flags, caller); + return __ioremap_caller(addr, size, flags, caller); +} + +void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags) { void *caller = __builtin_return_address(0); @@ -311,7 +321,8 @@ void iounmap(volatile void __iomem *token) } EXPORT_SYMBOL(ioremap); -EXPORT_SYMBOL(ioremap_flags); +EXPORT_SYMBOL(ioremap_wc); +EXPORT_SYMBOL(ioremap_prot); EXPORT_SYMBOL(__ioremap); EXPORT_SYMBOL(__ioremap_at); EXPORT_SYMBOL(iounmap); diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c index a8bc0d44393..9f09319352c 100644 --- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c +++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c @@ -97,7 +97,7 @@ cpld_pic_get_irq(int offset, u8 ignore, u8 __iomem *statusp, status |= (ignore | mask); if (status == 0xff) - return NO_IRQ_IGNORE; + return NO_IRQ; cpld_irq = ffz(status) + offset; @@ -109,14 +109,14 @@ cpld_pic_cascade(unsigned int irq, struct irq_desc *desc) { irq = cpld_pic_get_irq(0, PCI_IGNORE, &cpld_regs->pci_status, &cpld_regs->pci_mask); - if (irq != NO_IRQ && irq != NO_IRQ_IGNORE) { + if (irq != NO_IRQ) { generic_handle_irq(irq); return; } irq = cpld_pic_get_irq(8, MISC_IGNORE, &cpld_regs->misc_status, &cpld_regs->misc_mask); - if (irq != NO_IRQ && irq != NO_IRQ_IGNORE) { + if (irq != NO_IRQ) { generic_handle_irq(irq); return; } diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c index bb611819b83..1a9a4957057 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c @@ -486,7 +486,7 @@ void __init mpc52xx_init_irq(void) unsigned int mpc52xx_get_irq(void) { u32 status; - int irq = NO_IRQ_IGNORE; + int irq; status = in_be32(&intr->enc_status); if (status & 0x00000400) { /* critical */ @@ -509,6 +509,8 @@ unsigned int mpc52xx_get_irq(void) } else { irq |= (MPC52xx_IRQ_L1_PERP << MPC52xx_IRQ_L1_OFFSET); } + } else { + return NO_IRQ; } return irq_linear_revmap(mpc52xx_irqhost, irq); diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c index 5d6c34ce0cb..8ccf9ed62fe 100644 --- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c +++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c @@ -112,16 +112,8 @@ static int pci_pic_host_map(struct irq_host *h, unsigned int virq, return 0; } -static void pci_host_unmap(struct irq_host *h, unsigned int virq) -{ - /* remove chip and handler */ - irq_set_chip_data(virq, NULL); - irq_set_chip(virq, NULL); -} - static struct irq_host_ops pci_pic_host_ops = { .map = pci_pic_host_map, - .unmap = pci_host_unmap, }; int __init pq2ads_pci_init_irq(void) diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index fe3f6a3a530..d6a93a10c0f 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -235,8 +235,10 @@ void __init mpc85xx_smp_init(void) smp_85xx_ops.message_pass = smp_mpic_message_pass; } - if (cpu_has_feature(CPU_FTR_DBELL)) - smp_85xx_ops.message_pass = doorbell_message_pass; + if (cpu_has_feature(CPU_FTR_DBELL)) { + smp_85xx_ops.message_pass = smp_muxed_ipi_message_pass; + smp_85xx_ops.cause_ipi = doorbell_cause_ipi; + } BUG_ON(!smp_85xx_ops.message_pass); diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 6059053e715..f970ca2b180 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -57,16 +57,19 @@ config UDBG_RTAS_CONSOLE depends on PPC_RTAS default n +config PPC_SMP_MUXED_IPI + bool + help + Select this opton if your platform supports SMP and your + interrupt controller provides less than 4 interrupts to each + cpu. This will enable the generic code to multiplex the 4 + messages on to one ipi. + config PPC_UDBG_BEAT bool "BEAT based debug console" depends on PPC_CELLEB default n -config XICS - depends on PPC_PSERIES - bool - default y - config IPIC bool default n diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index a1e623822a3..2165b65876f 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -73,6 +73,7 @@ config PPC_BOOK3S_64 config PPC_BOOK3E_64 bool "Embedded processors" select PPC_FPU # Make it a choice ? + select PPC_SMP_MUXED_IPI endchoice @@ -178,6 +179,7 @@ config FSL_BOOKE config PPC_FSL_BOOK3E bool select FSL_EMB_PERFMON + select PPC_SMP_MUXED_IPI default y if FSL_BOOKE config PTE_64BIT diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile index 8839ef6c718..a4a89350bcf 100644 --- a/arch/powerpc/platforms/cell/Makefile +++ b/arch/powerpc/platforms/cell/Makefile @@ -43,7 +43,6 @@ obj-y += celleb_setup.o \ beat_hvCall.o beat_interrupt.o \ beat_iommu.o -obj-$(CONFIG_SMP) += beat_smp.o obj-$(CONFIG_PPC_UDBG_BEAT) += beat_udbg.o obj-$(CONFIG_SERIAL_TXX9) += celleb_scc_sio.o obj-$(CONFIG_SPU_BASE) += beat_spu_priv1.o diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index 1e3329e8578..ac06903e136 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -113,7 +113,7 @@ static void axon_msi_cascade(unsigned int irq, struct irq_desc *desc) pr_devel("axon_msi: woff %x roff %x msi %x\n", write_offset, msic->read_offset, msi); - if (msi < NR_IRQS && virq_to_host(msi) == msic->irq_host) { + if (msi < NR_IRQS && irq_get_chip_data(msi) == msic) { generic_handle_irq(msi); msic->fifo_virt[idx] = cpu_to_le32(0xffffffff); } else { @@ -320,6 +320,7 @@ static struct irq_chip msic_irq_chip = { static int msic_host_map(struct irq_host *h, unsigned int virq, irq_hw_number_t hw) { + irq_set_chip_data(virq, h->host_data); irq_set_chip_and_handler(virq, &msic_irq_chip, handle_simple_irq); return 0; diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c index 4cb9e147c30..55015e1f693 100644 --- a/arch/powerpc/platforms/cell/beat_interrupt.c +++ b/arch/powerpc/platforms/cell/beat_interrupt.c @@ -148,16 +148,6 @@ static int beatic_pic_host_map(struct irq_host *h, unsigned int virq, } /* - * Update binding hardware IRQ number (hw) and Virtuql - * IRQ number (virq). This is called only once for a given mapping. - */ -static void beatic_pic_host_remap(struct irq_host *h, unsigned int virq, - irq_hw_number_t hw) -{ - beat_construct_and_connect_irq_plug(virq, hw); -} - -/* * Translate device-tree interrupt spec to irq_hw_number_t style (ulong), * to pass away to irq_create_mapping(). * @@ -184,7 +174,6 @@ static int beatic_pic_host_match(struct irq_host *h, struct device_node *np) static struct irq_host_ops beatic_pic_host_ops = { .map = beatic_pic_host_map, - .remap = beatic_pic_host_remap, .unmap = beatic_pic_host_unmap, .xlate = beatic_pic_host_xlate, .match = beatic_pic_host_match, @@ -257,22 +246,6 @@ void __init beatic_init_IRQ(void) irq_set_default_host(beatic_host); } -#ifdef CONFIG_SMP - -/* Nullified to compile with SMP mode */ -void beatic_setup_cpu(int cpu) -{ -} - -void beatic_cause_IPI(int cpu, int mesg) -{ -} - -void beatic_request_IPIs(void) -{ -} -#endif /* CONFIG_SMP */ - void beatic_deinit_IRQ(void) { int i; diff --git a/arch/powerpc/platforms/cell/beat_interrupt.h b/arch/powerpc/platforms/cell/beat_interrupt.h index b470fd0051f..a7e52f91a07 100644 --- a/arch/powerpc/platforms/cell/beat_interrupt.h +++ b/arch/powerpc/platforms/cell/beat_interrupt.h @@ -24,9 +24,6 @@ extern void beatic_init_IRQ(void); extern unsigned int beatic_get_irq(void); -extern void beatic_cause_IPI(int cpu, int mesg); -extern void beatic_request_IPIs(void); -extern void beatic_setup_cpu(int); extern void beatic_deinit_IRQ(void); #endif diff --git a/arch/powerpc/platforms/cell/beat_smp.c b/arch/powerpc/platforms/cell/beat_smp.c deleted file mode 100644 index 3e86acbb0fb..00000000000 --- a/arch/powerpc/platforms/cell/beat_smp.c +++ /dev/null @@ -1,123 +0,0 @@ -/* - * SMP support for Celleb platform. (Incomplete) - * - * (C) Copyright 2006 TOSHIBA CORPORATION - * - * This code is based on arch/powerpc/platforms/cell/smp.c: - * Dave Engebretsen, Peter Bergner, and - * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com - * Plus various changes from other IBM teams... - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#undef DEBUG - -#include <linux/kernel.h> -#include <linux/smp.h> -#include <linux/interrupt.h> -#include <linux/init.h> -#include <linux/threads.h> -#include <linux/cpu.h> - -#include <asm/irq.h> -#include <asm/smp.h> -#include <asm/machdep.h> -#include <asm/udbg.h> - -#include "beat_interrupt.h" - -#ifdef DEBUG -#define DBG(fmt...) udbg_printf(fmt) -#else -#define DBG(fmt...) -#endif - -/* - * The primary thread of each non-boot processor is recorded here before - * smp init. - */ -/* static cpumask_t of_spin_map; */ - -/** - * smp_startup_cpu() - start the given cpu - * - * At boot time, there is nothing to do for primary threads which were - * started from Open Firmware. For anything else, call RTAS with the - * appropriate start location. - * - * Returns: - * 0 - failure - * 1 - success - */ -static inline int __devinit smp_startup_cpu(unsigned int lcpu) -{ - return 0; -} - -static void smp_beatic_message_pass(int target, int msg) -{ - unsigned int i; - - if (target < NR_CPUS) { - beatic_cause_IPI(target, msg); - } else { - for_each_online_cpu(i) { - if (target == MSG_ALL_BUT_SELF - && i == smp_processor_id()) - continue; - beatic_cause_IPI(i, msg); - } - } -} - -static int __init smp_beatic_probe(void) -{ - return cpumask_weight(cpu_possible_mask); -} - -static void __devinit smp_beatic_setup_cpu(int cpu) -{ - beatic_setup_cpu(cpu); -} - -static int __devinit smp_celleb_kick_cpu(int nr) -{ - BUG_ON(nr < 0 || nr >= NR_CPUS); - - return smp_startup_cpu(nr); -} - -static int smp_celleb_cpu_bootable(unsigned int nr) -{ - return 1; -} -static struct smp_ops_t bpa_beatic_smp_ops = { - .message_pass = smp_beatic_message_pass, - .probe = smp_beatic_probe, - .kick_cpu = smp_celleb_kick_cpu, - .setup_cpu = smp_beatic_setup_cpu, - .cpu_bootable = smp_celleb_cpu_bootable, -}; - -/* This is called very early */ -void __init smp_init_celleb(void) -{ - DBG(" -> smp_init_celleb()\n"); - - smp_ops = &bpa_beatic_smp_ops; - - DBG(" <- smp_init_celleb()\n"); -} diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c index 2904b0a6b2c..5822141aa63 100644 --- a/arch/powerpc/platforms/cell/celleb_pci.c +++ b/arch/powerpc/platforms/cell/celleb_pci.c @@ -319,7 +319,7 @@ static int __init celleb_setup_fake_pci_device(struct device_node *node, size = 256; config = &private->fake_config[devno][fn]; - *config = alloc_maybe_bootmem(size, GFP_KERNEL); + *config = zalloc_maybe_bootmem(size, GFP_KERNEL); if (*config == NULL) { printk(KERN_ERR "PCI: " "not enough memory for fake configuration space\n"); @@ -330,7 +330,7 @@ static int __init celleb_setup_fake_pci_device(struct device_node *node, size = sizeof(struct celleb_pci_resource); res = &private->res[devno][fn]; - *res = alloc_maybe_bootmem(size, GFP_KERNEL); + *res = zalloc_maybe_bootmem(size, GFP_KERNEL); if (*res == NULL) { printk(KERN_ERR "PCI: not enough memory for resource data space\n"); @@ -431,7 +431,7 @@ static int __init phb_set_bus_ranges(struct device_node *dev, static void __init celleb_alloc_private_mem(struct pci_controller *hose) { hose->private_data = - alloc_maybe_bootmem(sizeof(struct celleb_pci_private), + zalloc_maybe_bootmem(sizeof(struct celleb_pci_private), GFP_KERNEL); } diff --git a/arch/powerpc/platforms/cell/celleb_setup.c b/arch/powerpc/platforms/cell/celleb_setup.c index e5384557977..d58d9bae4b9 100644 --- a/arch/powerpc/platforms/cell/celleb_setup.c +++ b/arch/powerpc/platforms/cell/celleb_setup.c @@ -128,10 +128,6 @@ static void __init celleb_setup_arch_beat(void) spu_management_ops = &spu_management_of_ops; #endif -#ifdef CONFIG_SMP - smp_init_celleb(); -#endif - celleb_setup_arch_common(); } diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 44cfd1bef89..6a58744d66c 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -196,8 +196,20 @@ static irqreturn_t iic_ipi_action(int irq, void *dev_id) { int ipi = (int)(long)dev_id; - smp_message_recv(ipi); - + switch(ipi) { + case PPC_MSG_CALL_FUNCTION: + generic_smp_call_function_interrupt(); + break; + case PPC_MSG_RESCHEDULE: + /* Upcoming sched hook */ + break; + case PPC_MSG_CALL_FUNC_SINGLE: + generic_smp_call_function_single_interrupt(); + break; + case PPC_MSG_DEBUGGER_BREAK: + debug_ipi_action(0, NULL); + break; + } return IRQ_HANDLED; } static void iic_request_ipi(int ipi, const char *name) diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c index a2161b91b0b..d176e6148e3 100644 --- a/arch/powerpc/platforms/cell/smp.c +++ b/arch/powerpc/platforms/cell/smp.c @@ -103,22 +103,6 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu) return 1; } -static void smp_iic_message_pass(int target, int msg) -{ - unsigned int i; - - if (target < NR_CPUS) { - iic_cause_IPI(target, msg); - } else { - for_each_online_cpu(i) { - if (target == MSG_ALL_BUT_SELF - && i == smp_processor_id()) - continue; - iic_cause_IPI(i, msg); - } - } -} - static int __init smp_iic_probe(void) { iic_request_IPIs(); @@ -168,7 +152,7 @@ static int smp_cell_cpu_bootable(unsigned int nr) return 1; } static struct smp_ops_t bpa_iic_smp_ops = { - .message_pass = smp_iic_message_pass, + .message_pass = iic_cause_IPI, .probe = smp_iic_probe, .kick_cpu = smp_cell_kick_cpu, .setup_cpu = smp_cell_setup_cpu, diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c index 34d2b99d10c..442c28c00f8 100644 --- a/arch/powerpc/platforms/cell/spider-pic.c +++ b/arch/powerpc/platforms/cell/spider-pic.c @@ -68,9 +68,9 @@ struct spider_pic { }; static struct spider_pic spider_pics[SPIDER_CHIP_COUNT]; -static struct spider_pic *spider_virq_to_pic(unsigned int virq) +static struct spider_pic *spider_irq_data_to_pic(struct irq_data *d) { - return virq_to_host(virq)->host_data; + return irq_data_get_irq_chip_data(d); } static void __iomem *spider_get_irq_config(struct spider_pic *pic, @@ -81,7 +81,7 @@ static void __iomem *spider_get_irq_config(struct spider_pic *pic, static void spider_unmask_irq(struct irq_data *d) { - struct spider_pic *pic = spider_virq_to_pic(d->irq); + struct spider_pic *pic = spider_irq_data_to_pic(d); void __iomem *cfg = spider_get_irq_config(pic, irqd_to_hwirq(d)); out_be32(cfg, in_be32(cfg) | 0x30000000u); @@ -89,7 +89,7 @@ static void spider_unmask_irq(struct irq_data *d) static void spider_mask_irq(struct irq_data *d) { - struct spider_pic *pic = spider_virq_to_pic(d->irq); + struct spider_pic *pic = spider_irq_data_to_pic(d); void __iomem *cfg = spider_get_irq_config(pic, irqd_to_hwirq(d)); out_be32(cfg, in_be32(cfg) & ~0x30000000u); @@ -97,7 +97,7 @@ static void spider_mask_irq(struct irq_data *d) static void spider_ack_irq(struct irq_data *d) { - struct spider_pic *pic = spider_virq_to_pic(d->irq); + struct spider_pic *pic = spider_irq_data_to_pic(d); unsigned int src = irqd_to_hwirq(d); /* Reset edge detection logic if necessary @@ -116,7 +116,7 @@ static void spider_ack_irq(struct irq_data *d) static int spider_set_irq_type(struct irq_data *d, unsigned int type) { unsigned int sense = type & IRQ_TYPE_SENSE_MASK; - struct spider_pic *pic = spider_virq_to_pic(d->irq); + struct spider_pic *pic = spider_irq_data_to_pic(d); unsigned int hw = irqd_to_hwirq(d); void __iomem *cfg = spider_get_irq_config(pic, hw); u32 old_mask; @@ -171,6 +171,7 @@ static struct irq_chip spider_pic = { static int spider_host_map(struct irq_host *h, unsigned int virq, irq_hw_number_t hw) { + irq_set_chip_data(virq, h->host_data); irq_set_chip_and_handler(virq, &spider_pic, handle_level_irq); /* Set default irq type */ diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c index 77cbe4c8f95..f61a2dd96b9 100644 --- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c +++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c @@ -107,12 +107,6 @@ static int flipper_pic_map(struct irq_host *h, unsigned int virq, return 0; } -static void flipper_pic_unmap(struct irq_host *h, unsigned int irq) -{ - irq_set_chip_data(irq, NULL); - irq_set_chip(irq, NULL); -} - static int flipper_pic_match(struct irq_host *h, struct device_node *np) { return 1; @@ -121,7 +115,6 @@ static int flipper_pic_match(struct irq_host *h, struct device_node *np) static struct irq_host_ops flipper_irq_host_ops = { .map = flipper_pic_map, - .unmap = flipper_pic_unmap, .match = flipper_pic_match, }; diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c index 44b398b0a2f..e4919170c6b 100644 --- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c +++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c @@ -100,15 +100,8 @@ static int hlwd_pic_map(struct irq_host *h, unsigned int virq, return 0; } -static void hlwd_pic_unmap(struct irq_host *h, unsigned int irq) -{ - irq_set_chip_data(irq, NULL); - irq_set_chip(irq, NULL); -} - static struct irq_host_ops hlwd_irq_host_ops = { .map = hlwd_pic_map, - .unmap = hlwd_pic_unmap, }; static unsigned int __hlwd_pic_get_irq(struct irq_host *h) diff --git a/arch/powerpc/platforms/iseries/Kconfig b/arch/powerpc/platforms/iseries/Kconfig index ea1d3622b41..b57cda3a081 100644 --- a/arch/powerpc/platforms/iseries/Kconfig +++ b/arch/powerpc/platforms/iseries/Kconfig @@ -1,6 +1,7 @@ config PPC_ISERIES bool "IBM Legacy iSeries" depends on PPC64 && PPC_BOOK3S + select PPC_SMP_MUXED_IPI select PPC_INDIRECT_PIO select PPC_INDIRECT_MMIO select PPC_PCI_CHOICE if EXPERT diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S index a67984c0495..29c02f36b32 100644 --- a/arch/powerpc/platforms/iseries/exception.S +++ b/arch/powerpc/platforms/iseries/exception.S @@ -61,29 +61,31 @@ system_reset_iSeries: /* Spin on __secondary_hold_spinloop until it is updated by the boot cpu. */ /* In the UP case we'll yield() later, and we will not access the paca anyway */ #ifdef CONFIG_SMP -1: +iSeries_secondary_wait_paca: HMT_LOW LOAD_REG_ADDR(r23, __secondary_hold_spinloop) ld r23,0(r23) - sync - LOAD_REG_ADDR(r3,current_set) - sldi r28,r24,3 /* get current_set[cpu#] */ - ldx r3,r3,r28 - addi r1,r3,THREAD_SIZE - subi r1,r1,STACK_FRAME_OVERHEAD - cmpwi 0,r23,0 /* Keep poking the Hypervisor until */ - bne 2f /* we're released */ - /* Let the Hypervisor know we are alive */ + cmpdi 0,r23,0 + bne 2f /* go on when the master is ready */ + + /* Keep poking the Hypervisor until we're released */ /* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */ lis r3,0x8002 rldicr r3,r3,32,15 /* r0 = (r3 << 32) & 0xffff000000000000 */ li r0,-1 /* r0=-1 indicates a Hypervisor call */ sc /* Invoke the hypervisor via a system call */ - b 1b -#endif + b iSeries_secondary_wait_paca 2: + HMT_MEDIUM + sync + + LOAD_REG_ADDR(r3, nr_cpu_ids) /* get number of pacas allocated */ + lwz r3,0(r3) /* nr_cpus= or NR_CPUS can limit */ + cmpld 0,r24,r3 /* is our cpu number allocated? */ + bge iSeries_secondary_yield /* no, yield forever */ + /* Load our paca now that it's been allocated */ LOAD_REG_ADDR(r13, paca) ld r13,0(r13) @@ -94,10 +96,24 @@ system_reset_iSeries: ori r23,r23,MSR_RI mtmsrd r23 /* RI on */ - HMT_LOW -#ifdef CONFIG_SMP +iSeries_secondary_smp_loop: lbz r23,PACAPROCSTART(r13) /* Test if this processor * should start */ + cmpwi 0,r23,0 + bne 3f /* go on when we are told */ + + HMT_LOW + /* Let the Hypervisor know we are alive */ + /* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */ + lis r3,0x8002 + rldicr r3,r3,32,15 /* r0 = (r3 << 32) & 0xffff000000000000 */ + li r0,-1 /* r0=-1 indicates a Hypervisor call */ + sc /* Invoke the hypervisor via a system call */ + mfspr r13,SPRN_SPRG_PACA /* Put r13 back ???? */ + b iSeries_secondary_smp_loop /* wait for signal to start */ + +3: + HMT_MEDIUM sync LOAD_REG_ADDR(r3,current_set) sldi r28,r24,3 /* get current_set[cpu#] */ @@ -105,27 +121,22 @@ system_reset_iSeries: addi r1,r3,THREAD_SIZE subi r1,r1,STACK_FRAME_OVERHEAD - cmpwi 0,r23,0 - beq iSeries_secondary_smp_loop /* Loop until told to go */ b __secondary_start /* Loop until told to go */ -iSeries_secondary_smp_loop: - /* Let the Hypervisor know we are alive */ - /* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */ - lis r3,0x8002 - rldicr r3,r3,32,15 /* r0 = (r3 << 32) & 0xffff000000000000 */ -#else /* CONFIG_SMP */ +#endif /* CONFIG_SMP */ + +iSeries_secondary_yield: /* Yield the processor. This is required for non-SMP kernels which are running on multi-threaded machines. */ + HMT_LOW lis r3,0x8000 rldicr r3,r3,32,15 /* r3 = (r3 << 32) & 0xffff000000000000 */ addi r3,r3,18 /* r3 = 0x8000000000000012 which is "yield" */ li r4,0 /* "yield timed" */ li r5,-1 /* "yield forever" */ -#endif /* CONFIG_SMP */ li r0,-1 /* r0=-1 indicates a Hypervisor call */ sc /* Invoke the hypervisor via a system call */ mfspr r13,SPRN_SPRG_PACA /* Put r13 back ???? */ - b 2b /* If SMP not configured, secondaries + b iSeries_secondary_yield /* If SMP not configured, secondaries * loop forever */ /*** ISeries-LPAR interrupt handlers ***/ diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c index 375c21ca660..b2103453eb0 100644 --- a/arch/powerpc/platforms/iseries/irq.c +++ b/arch/powerpc/platforms/iseries/irq.c @@ -42,7 +42,6 @@ #include "irq.h" #include "pci.h" #include "call_pci.h" -#include "smp.h" #ifdef CONFIG_PCI @@ -316,7 +315,7 @@ unsigned int iSeries_get_irq(void) #ifdef CONFIG_SMP if (get_lppaca()->int_dword.fields.ipi_cnt) { get_lppaca()->int_dword.fields.ipi_cnt = 0; - iSeries_smp_message_recv(); + smp_ipi_demux(); } #endif /* CONFIG_SMP */ if (hvlpevent_is_pending()) diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index 81cb8d2c413..c25a0815c26 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -685,6 +685,11 @@ void * __init iSeries_early_setup(void) powerpc_firmware_features |= FW_FEATURE_ISERIES; powerpc_firmware_features |= FW_FEATURE_LPAR; +#ifdef CONFIG_SMP + /* On iSeries we know we can never have more than 64 cpus */ + nr_cpu_ids = max(nr_cpu_ids, 64); +#endif + iSeries_fixup_klimit(); /* diff --git a/arch/powerpc/platforms/iseries/smp.c b/arch/powerpc/platforms/iseries/smp.c index 02a677a1f91..e3265adde5d 100644 --- a/arch/powerpc/platforms/iseries/smp.c +++ b/arch/powerpc/platforms/iseries/smp.c @@ -42,45 +42,11 @@ #include <asm/cputable.h> #include <asm/system.h> -#include "smp.h" - -static unsigned long iSeries_smp_message[NR_CPUS]; - -void iSeries_smp_message_recv(void) +static void smp_iSeries_cause_ipi(int cpu, unsigned long data) { - int cpu = smp_processor_id(); - int msg; - - if (num_online_cpus() < 2) - return; - - for (msg = 0; msg < 4; msg++) - if (test_and_clear_bit(msg, &iSeries_smp_message[cpu])) - smp_message_recv(msg); -} - -static inline void smp_iSeries_do_message(int cpu, int msg) -{ - set_bit(msg, &iSeries_smp_message[cpu]); HvCall_sendIPI(&(paca[cpu])); } -static void smp_iSeries_message_pass(int target, int msg) -{ - int i; - - if (target < NR_CPUS) - smp_iSeries_do_message(target, msg); - else { - for_each_online_cpu(i) { - if ((target == MSG_ALL_BUT_SELF) && - (i == smp_processor_id())) - continue; - smp_iSeries_do_message(i, msg); - } - } -} - static int smp_iSeries_probe(void) { return cpumask_weight(cpu_possible_mask); @@ -109,7 +75,8 @@ static void __devinit smp_iSeries_setup_cpu(int nr) } static struct smp_ops_t iSeries_smp_ops = { - .message_pass = smp_iSeries_message_pass, + .message_pass = smp_muxed_ipi_message_pass, + .cause_ipi = smp_iSeries_cause_ipi, .probe = smp_iSeries_probe, .kick_cpu = smp_iSeries_kick_cpu, .setup_cpu = smp_iSeries_setup_cpu, diff --git a/arch/powerpc/platforms/iseries/smp.h b/arch/powerpc/platforms/iseries/smp.h deleted file mode 100644 index d501f7de01e..00000000000 --- a/arch/powerpc/platforms/iseries/smp.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _PLATFORMS_ISERIES_SMP_H -#define _PLATFORMS_ISERIES_SMP_H - -extern void iSeries_smp_message_recv(void); - -#endif /* _PLATFORMS_ISERIES_SMP_H */ diff --git a/arch/powerpc/platforms/powermac/Kconfig b/arch/powerpc/platforms/powermac/Kconfig index 1e1a0873e1d..1afd10f6785 100644 --- a/arch/powerpc/platforms/powermac/Kconfig +++ b/arch/powerpc/platforms/powermac/Kconfig @@ -18,4 +18,13 @@ config PPC_PMAC64 select PPC_970_NAP default y - +config PPC_PMAC32_PSURGE + bool "Support for powersurge upgrade cards" if EXPERT + depends on SMP && PPC32 && PPC_PMAC + select PPC_SMP_MUXED_IPI + default y + help + The powersurge cpu boards can be used in the generation + of powermacs that have a socket for an upgradeable cpu card, + including the 7500, 8500, 9500, 9600. Support exists for + both dual and quad socket upgrade cards. diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 2f34ad04029..360260d1352 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -239,15 +239,12 @@ static unsigned int pmac_pic_get_irq(void) unsigned long bits = 0; unsigned long flags; -#ifdef CONFIG_SMP - void psurge_smp_message_recv(void); - - /* IPI's are a hack on the powersurge -- Cort */ - if ( smp_processor_id() != 0 ) { - psurge_smp_message_recv(); - return NO_IRQ_IGNORE; /* ignore, already handled */ +#ifdef CONFIG_PPC_PMAC32_PSURGE + /* IPI's are a hack on the powersurge -- Cort */ + if (smp_processor_id() != 0) { + return psurge_secondary_virq; } -#endif /* CONFIG_SMP */ +#endif /* CONFIG_PPC_PMAC32_PSURGE */ raw_spin_lock_irqsave(&pmac_pic_lock, flags); for (irq = max_real_irqs; (irq -= 32) >= 0; ) { int i = irq >> 5; diff --git a/arch/powerpc/platforms/powermac/pic.h b/arch/powerpc/platforms/powermac/pic.h deleted file mode 100644 index d622a8345aa..00000000000 --- a/arch/powerpc/platforms/powermac/pic.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef __PPC_PLATFORMS_PMAC_PIC_H -#define __PPC_PLATFORMS_PMAC_PIC_H - -#include <linux/irq.h> - -extern struct irq_chip pmac_pic; - -extern void pmac_pic_init(void); -extern int pmac_get_irq(void); - -#endif /* __PPC_PLATFORMS_PMAC_PIC_H */ diff --git a/arch/powerpc/platforms/powermac/pmac.h b/arch/powerpc/platforms/powermac/pmac.h index 20468f49aec..8327cce2bdb 100644 --- a/arch/powerpc/platforms/powermac/pmac.h +++ b/arch/powerpc/platforms/powermac/pmac.h @@ -33,6 +33,7 @@ extern void pmac_setup_pci_dma(void); extern void pmac_check_ht_link(void); extern void pmac_setup_smp(void); +extern int psurge_secondary_virq; extern void low_cpu_die(void) __attribute__((noreturn)); extern int pmac_nvram_init(void); diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index 621d4b7755f..db092d7c4c5 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -70,7 +70,7 @@ static void (*pmac_tb_freeze)(int freeze); static u64 timebase; static int tb_req; -#ifdef CONFIG_PPC32 +#ifdef CONFIG_PPC_PMAC32_PSURGE /* * Powersurge (old powermac SMP) support. @@ -124,6 +124,10 @@ static volatile u32 __iomem *psurge_start; /* what sort of powersurge board we have */ static int psurge_type = PSURGE_NONE; +/* irq for secondary cpus to report */ +static struct irq_host *psurge_host; +int psurge_secondary_virq; + /* * Set and clear IPIs for powersurge. */ @@ -156,51 +160,52 @@ static inline void psurge_clr_ipi(int cpu) /* * On powersurge (old SMP powermac architecture) we don't have * separate IPIs for separate messages like openpic does. Instead - * we have a bitmap for each processor, where a 1 bit means that - * the corresponding message is pending for that processor. - * Ideally each cpu's entry would be in a different cache line. + * use the generic demux helpers * -- paulus. */ -static unsigned long psurge_smp_message[NR_CPUS]; - -void psurge_smp_message_recv(void) +static irqreturn_t psurge_ipi_intr(int irq, void *d) { - int cpu = smp_processor_id(); - int msg; - - /* clear interrupt */ - psurge_clr_ipi(cpu); + psurge_clr_ipi(smp_processor_id()); + smp_ipi_demux(); - if (num_online_cpus() < 2) - return; + return IRQ_HANDLED; +} - /* make sure there is a message there */ - for (msg = 0; msg < 4; msg++) - if (test_and_clear_bit(msg, &psurge_smp_message[cpu])) - smp_message_recv(msg); +static void smp_psurge_cause_ipi(int cpu, unsigned long data) +{ + psurge_set_ipi(cpu); } -irqreturn_t psurge_primary_intr(int irq, void *d) +static int psurge_host_map(struct irq_host *h, unsigned int virq, + irq_hw_number_t hw) { - psurge_smp_message_recv(); - return IRQ_HANDLED; + irq_set_chip_and_handler(virq, &dummy_irq_chip, handle_percpu_irq); + + return 0; } -static void smp_psurge_message_pass(int target, int msg) +struct irq_host_ops psurge_host_ops = { + .map = psurge_host_map, +}; + +static int psurge_secondary_ipi_init(void) { - int i; + int rc = -ENOMEM; - if (num_online_cpus() < 2) - return; + psurge_host = irq_alloc_host(NULL, IRQ_HOST_MAP_NOMAP, 0, + &psurge_host_ops, 0); - for_each_online_cpu(i) { - if (target == MSG_ALL - || (target == MSG_ALL_BUT_SELF && i != smp_processor_id()) - || target == i) { - set_bit(msg, &psurge_smp_message[i]); - psurge_set_ipi(i); - } - } + if (psurge_host) + psurge_secondary_virq = irq_create_direct_mapping(psurge_host); + + if (psurge_secondary_virq) + rc = request_irq(psurge_secondary_virq, psurge_ipi_intr, + IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL); + + if (rc) + pr_err("Failed to setup secondary cpu IPI\n"); + + return rc; } /* @@ -311,6 +316,9 @@ static int __init smp_psurge_probe(void) ncpus = 2; } + if (psurge_secondary_ipi_init()) + return 1; + psurge_start = ioremap(PSURGE_START, 4); psurge_pri_intr = ioremap(PSURGE_PRI_INTR, 4); @@ -399,8 +407,8 @@ static int __init smp_psurge_kick_cpu(int nr) } static struct irqaction psurge_irqaction = { - .handler = psurge_primary_intr, - .flags = IRQF_DISABLED, + .handler = psurge_ipi_intr, + .flags = IRQF_DISABLED|IRQF_PERCPU, .name = "primary IPI", }; @@ -439,14 +447,15 @@ void __init smp_psurge_give_timebase(void) /* PowerSurge-style Macs */ struct smp_ops_t psurge_smp_ops = { - .message_pass = smp_psurge_message_pass, + .message_pass = smp_muxed_ipi_message_pass, + .cause_ipi = smp_psurge_cause_ipi, .probe = smp_psurge_probe, .kick_cpu = smp_psurge_kick_cpu, .setup_cpu = smp_psurge_setup_cpu, .give_timebase = smp_psurge_give_timebase, .take_timebase = smp_psurge_take_timebase, }; -#endif /* CONFIG_PPC32 - actually powersurge support */ +#endif /* CONFIG_PPC_PMAC32_PSURGE */ /* * Core 99 and later support @@ -1006,7 +1015,7 @@ void __init pmac_setup_smp(void) of_node_put(np); smp_ops = &core99_smp_ops; } -#ifdef CONFIG_PPC32 +#ifdef CONFIG_PPC_PMAC32_PSURGE else { /* We have to set bits in cpu_possible_mask here since the * secondary CPU(s) aren't in the device tree. Various @@ -1019,7 +1028,7 @@ void __init pmac_setup_smp(void) set_cpu_possible(cpu, true); smp_ops = &psurge_smp_ops; } -#endif /* CONFIG_PPC32 */ +#endif /* CONFIG_PPC_PMAC32_PSURGE */ #ifdef CONFIG_HOTPLUG_CPU ppc_md.cpu_die = pmac_cpu_die; diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c index 523bd0d34d9..600ed2c0ed5 100644 --- a/arch/powerpc/platforms/ps3/interrupt.c +++ b/arch/powerpc/platforms/ps3/interrupt.c @@ -659,11 +659,6 @@ static void __maybe_unused _dump_mask(struct ps3_private *pd, static void dump_bmp(struct ps3_private* pd) {}; #endif /* defined(DEBUG) */ -static void ps3_host_unmap(struct irq_host *h, unsigned int virq) -{ - irq_set_chip_data(virq, NULL); -} - static int ps3_host_map(struct irq_host *h, unsigned int virq, irq_hw_number_t hwirq) { @@ -683,7 +678,6 @@ static int ps3_host_match(struct irq_host *h, struct device_node *np) static struct irq_host_ops ps3_host_ops = { .map = ps3_host_map, - .unmap = ps3_host_unmap, .match = ps3_host_match, }; diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c index 51ffde40af2..4c44794faac 100644 --- a/arch/powerpc/platforms/ps3/smp.c +++ b/arch/powerpc/platforms/ps3/smp.c @@ -39,7 +39,7 @@ #define MSG_COUNT 4 static DEFINE_PER_CPU(unsigned int [MSG_COUNT], ps3_ipi_virqs); -static void do_message_pass(int target, int msg) +static void ps3_smp_message_pass(int cpu, int msg) { int result; unsigned int virq; @@ -49,28 +49,12 @@ static void do_message_pass(int target, int msg) return; } - virq = per_cpu(ps3_ipi_virqs, target)[msg]; + virq = per_cpu(ps3_ipi_virqs, cpu)[msg]; result = ps3_send_event_locally(virq); if (result) DBG("%s:%d: ps3_send_event_locally(%d, %d) failed" - " (%d)\n", __func__, __LINE__, target, msg, result); -} - -static void ps3_smp_message_pass(int target, int msg) -{ - int cpu; - - if (target < NR_CPUS) - do_message_pass(target, msg); - else if (target == MSG_ALL_BUT_SELF) { - for_each_online_cpu(cpu) - if (cpu != smp_processor_id()) - do_message_pass(cpu, msg); - } else { - for_each_online_cpu(cpu) - do_message_pass(cpu, msg); - } + " (%d)\n", __func__, __LINE__, cpu, msg, result); } static int ps3_smp_probe(void) diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c index 39a472e9e80..375a9f92158 100644 --- a/arch/powerpc/platforms/ps3/spu.c +++ b/arch/powerpc/platforms/ps3/spu.c @@ -197,7 +197,7 @@ static void spu_unmap(struct spu *spu) * The current HV requires the spu shadow regs to be mapped with the * PTE page protection bits set as read-only (PP=3). This implementation * uses the low level __ioremap() to bypass the page protection settings - * inforced by ioremap_flags() to get the needed PTE bits set for the + * inforced by ioremap_prot() to get the needed PTE bits set for the * shadow regs. */ @@ -214,7 +214,7 @@ static int __init setup_areas(struct spu *spu) goto fail_ioremap; } - spu->local_store = (__force void *)ioremap_flags(spu->local_store_phys, + spu->local_store = (__force void *)ioremap_prot(spu->local_store_phys, LS_SIZE, _PAGE_NO_CACHE); if (!spu->local_store) { diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index c371bc06434..e9190073bb9 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -52,10 +52,10 @@ static u8 dtl_event_mask = 0x7; /* - * Size of per-cpu log buffers. Default is just under 16 pages worth. + * Size of per-cpu log buffers. Firmware requires that the buffer does + * not cross a 4k boundary. */ -static int dtl_buf_entries = (16 * 85); - +static int dtl_buf_entries = N_DISPATCH_LOG; #ifdef CONFIG_VIRT_CPU_ACCOUNTING struct dtl_ring { @@ -151,7 +151,7 @@ static int dtl_start(struct dtl *dtl) /* Register our dtl buffer with the hypervisor. The HV expects the * buffer size to be passed in the second word of the buffer */ - ((u32 *)dtl->buf)[1] = dtl->buf_entries * sizeof(struct dtl_entry); + ((u32 *)dtl->buf)[1] = DISPATCH_LOG_BYTES; hwcpu = get_hard_smp_processor_id(dtl->cpu); addr = __pa(dtl->buf); @@ -196,13 +196,15 @@ static int dtl_enable(struct dtl *dtl) long int rc; struct dtl_entry *buf = NULL; + if (!dtl_cache) + return -ENOMEM; + /* only allow one reader */ if (dtl->buf) return -EBUSY; n_entries = dtl_buf_entries; - buf = kmalloc_node(n_entries * sizeof(struct dtl_entry), - GFP_KERNEL, cpu_to_node(dtl->cpu)); + buf = kmem_cache_alloc_node(dtl_cache, GFP_KERNEL, cpu_to_node(dtl->cpu)); if (!buf) { printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n", __func__, dtl->cpu); @@ -223,7 +225,7 @@ static int dtl_enable(struct dtl *dtl) spin_unlock(&dtl->lock); if (rc) - kfree(buf); + kmem_cache_free(dtl_cache, buf); return rc; } @@ -231,7 +233,7 @@ static void dtl_disable(struct dtl *dtl) { spin_lock(&dtl->lock); dtl_stop(dtl); - kfree(dtl->buf); + kmem_cache_free(dtl_cache, dtl->buf); dtl->buf = NULL; dtl->buf_entries = 0; spin_unlock(&dtl->lock); @@ -365,7 +367,7 @@ static int dtl_init(void) event_mask_file = debugfs_create_x8("dtl_event_mask", 0600, dtl_dir, &dtl_event_mask); - buf_entries_file = debugfs_create_u32("dtl_buf_entries", 0600, + buf_entries_file = debugfs_create_u32("dtl_buf_entries", 0400, dtl_dir, &dtl_buf_entries); if (!event_mask_file || !buf_entries_file) { diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 6d5412a18b2..01faab9456c 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -659,15 +659,18 @@ static void remove_ddw(struct device_node *np) { struct dynamic_dma_window_prop *dwp; struct property *win64; - const u32 *ddr_avail; + const u32 *ddw_avail; u64 liobn; int len, ret; - ddr_avail = of_get_property(np, "ibm,ddw-applicable", &len); + ddw_avail = of_get_property(np, "ibm,ddw-applicable", &len); win64 = of_find_property(np, DIRECT64_PROPNAME, NULL); - if (!win64 || !ddr_avail || len < 3 * sizeof(u32)) + if (!win64) return; + if (!ddw_avail || len < 3 * sizeof(u32) || win64->length < sizeof(*dwp)) + goto delprop; + dwp = win64->value; liobn = (u64)be32_to_cpu(dwp->liobn); @@ -681,28 +684,29 @@ static void remove_ddw(struct device_node *np) pr_debug("%s successfully cleared tces in window.\n", np->full_name); - ret = rtas_call(ddr_avail[2], 1, 1, NULL, liobn); + ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn); if (ret) pr_warning("%s: failed to remove direct window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np->full_name, ret, ddr_avail[2], liobn); + np->full_name, ret, ddw_avail[2], liobn); else pr_debug("%s: successfully removed direct window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np->full_name, ret, ddr_avail[2], liobn); -} + np->full_name, ret, ddw_avail[2], liobn); +delprop: + ret = prom_remove_property(np, win64); + if (ret) + pr_warning("%s: failed to remove direct window property: %d\n", + np->full_name, ret); +} -static int dupe_ddw_if_already_created(struct pci_dev *dev, struct device_node *pdn) +static u64 find_existing_ddw(struct device_node *pdn) { - struct device_node *dn; - struct pci_dn *pcidn; struct direct_window *window; const struct dynamic_dma_window_prop *direct64; u64 dma_addr = 0; - dn = pci_device_to_OF_node(dev); - pcidn = PCI_DN(dn); spin_lock(&direct_window_list_lock); /* check if we already created a window and dupe that config if so */ list_for_each_entry(window, &direct_window_list, list) { @@ -717,36 +721,40 @@ static int dupe_ddw_if_already_created(struct pci_dev *dev, struct device_node * return dma_addr; } -static u64 dupe_ddw_if_kexec(struct pci_dev *dev, struct device_node *pdn) +static int find_existing_ddw_windows(void) { - struct device_node *dn; - struct pci_dn *pcidn; int len; + struct device_node *pdn; struct direct_window *window; const struct dynamic_dma_window_prop *direct64; - u64 dma_addr = 0; - dn = pci_device_to_OF_node(dev); - pcidn = PCI_DN(dn); - direct64 = of_get_property(pdn, DIRECT64_PROPNAME, &len); - if (direct64) { + if (!firmware_has_feature(FW_FEATURE_LPAR)) + return 0; + + for_each_node_with_property(pdn, DIRECT64_PROPNAME) { + direct64 = of_get_property(pdn, DIRECT64_PROPNAME, &len); + if (!direct64) + continue; + window = kzalloc(sizeof(*window), GFP_KERNEL); - if (!window) { + if (!window || len < sizeof(struct dynamic_dma_window_prop)) { + kfree(window); remove_ddw(pdn); - } else { - window->device = pdn; - window->prop = direct64; - spin_lock(&direct_window_list_lock); - list_add(&window->list, &direct_window_list); - spin_unlock(&direct_window_list_lock); - dma_addr = direct64->dma_base; + continue; } + + window->device = pdn; + window->prop = direct64; + spin_lock(&direct_window_list_lock); + list_add(&window->list, &direct_window_list); + spin_unlock(&direct_window_list_lock); } - return dma_addr; + return 0; } +machine_arch_initcall(pseries, find_existing_ddw_windows); -static int query_ddw(struct pci_dev *dev, const u32 *ddr_avail, +static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, struct ddw_query_response *query) { struct device_node *dn; @@ -767,15 +775,15 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddr_avail, if (pcidn->eeh_pe_config_addr) cfg_addr = pcidn->eeh_pe_config_addr; buid = pcidn->phb->buid; - ret = rtas_call(ddr_avail[0], 3, 5, (u32 *)query, + ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query, cfg_addr, BUID_HI(buid), BUID_LO(buid)); dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x" - " returned %d\n", ddr_avail[0], cfg_addr, BUID_HI(buid), + " returned %d\n", ddw_avail[0], cfg_addr, BUID_HI(buid), BUID_LO(buid), ret); return ret; } -static int create_ddw(struct pci_dev *dev, const u32 *ddr_avail, +static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, struct ddw_create_response *create, int page_shift, int window_shift) { @@ -800,12 +808,12 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddr_avail, do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ - ret = rtas_call(ddr_avail[1], 5, 4, (u32 *)create, cfg_addr, + ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, cfg_addr, BUID_HI(buid), BUID_LO(buid), page_shift, window_shift); } while (rtas_busy_delay(ret)); dev_info(&dev->dev, "ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d " - "(liobn = 0x%x starting addr = %x %x)\n", ddr_avail[1], + "(liobn = 0x%x starting addr = %x %x)\n", ddw_avail[1], cfg_addr, BUID_HI(buid), BUID_LO(buid), page_shift, window_shift, ret, create->liobn, create->addr_hi, create->addr_lo); @@ -831,18 +839,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) int page_shift; u64 dma_addr, max_addr; struct device_node *dn; - const u32 *uninitialized_var(ddr_avail); + const u32 *uninitialized_var(ddw_avail); struct direct_window *window; - struct property *uninitialized_var(win64); + struct property *win64; struct dynamic_dma_window_prop *ddwprop; mutex_lock(&direct_window_init_mutex); - dma_addr = dupe_ddw_if_already_created(dev, pdn); - if (dma_addr != 0) - goto out_unlock; - - dma_addr = dupe_ddw_if_kexec(dev, pdn); + dma_addr = find_existing_ddw(pdn); if (dma_addr != 0) goto out_unlock; @@ -854,8 +858,8 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * for the given node in that order. * the property is actually in the parent, not the PE */ - ddr_avail = of_get_property(pdn, "ibm,ddw-applicable", &len); - if (!ddr_avail || len < 3 * sizeof(u32)) + ddw_avail = of_get_property(pdn, "ibm,ddw-applicable", &len); + if (!ddw_avail || len < 3 * sizeof(u32)) goto out_unlock; /* @@ -865,7 +869,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * of page sizes: supported and supported for migrate-dma. */ dn = pci_device_to_OF_node(dev); - ret = query_ddw(dev, ddr_avail, &query); + ret = query_ddw(dev, ddw_avail, &query); if (ret != 0) goto out_unlock; @@ -907,13 +911,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) } win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL); win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL); + win64->length = sizeof(*ddwprop); if (!win64->name || !win64->value) { dev_info(&dev->dev, "couldn't allocate property name and value\n"); goto out_free_prop; } - ret = create_ddw(dev, ddr_avail, &create, page_shift, len); + ret = create_ddw(dev, ddw_avail, &create, page_shift, len); if (ret != 0) goto out_free_prop; @@ -1021,13 +1026,16 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) const void *dma_window = NULL; u64 dma_offset; - if (!dev->dma_mask || !dma_supported(dev, dma_mask)) + if (!dev->dma_mask) return -EIO; + if (!dev_is_pci(dev)) + goto check_mask; + + pdev = to_pci_dev(dev); + /* only attempt to use a new window if 64-bit DMA is requested */ if (!disable_ddw && dma_mask == DMA_BIT_MASK(64)) { - pdev = to_pci_dev(dev); - dn = pci_device_to_OF_node(pdev); dev_dbg(dev, "node is %s\n", dn->full_name); @@ -1054,12 +1062,17 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) } } - /* fall-through to iommu ops */ - if (!ddw_enabled) { - dev_info(dev, "Using 32-bit DMA via iommu\n"); + /* fall back on iommu ops, restore table pointer with ops */ + if (!ddw_enabled && get_dma_ops(dev) != &dma_iommu_ops) { + dev_info(dev, "Restoring 32-bit DMA via iommu\n"); set_dma_ops(dev, &dma_iommu_ops); + pci_dma_dev_setup_pSeriesLP(pdev); } +check_mask: + if (!dma_supported(dev, dma_mask)) + return -EIO; + *dev->dma_mask = dma_mask; return 0; } diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 164a8eb4592..086d2ae4e06 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -227,7 +227,7 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) struct rtas_error_log *h, *errhdr = NULL; if (!VALID_FWNMI_BUFFER(regs->gpr[3])) { - printk(KERN_ERR "FWNMI: corrupt r3\n"); + printk(KERN_ERR "FWNMI: corrupt r3 0x%016lx\n", regs->gpr[3]); return NULL; } diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 1689adccc6d..593acceeff9 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -278,6 +278,8 @@ static struct notifier_block pci_dn_reconfig_nb = { .notifier_call = pci_dn_reconfig_notifier, }; +struct kmem_cache *dtl_cache; + #ifdef CONFIG_VIRT_CPU_ACCOUNTING /* * Allocate space for the dispatch trace log for all possible cpus @@ -289,18 +291,12 @@ static int alloc_dispatch_logs(void) int cpu, ret; struct paca_struct *pp; struct dtl_entry *dtl; - struct kmem_cache *dtl_cache; if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return 0; - dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES, - DISPATCH_LOG_BYTES, 0, NULL); - if (!dtl_cache) { - pr_warn("Failed to create dispatch trace log buffer cache\n"); - pr_warn("Stolen time statistics will be unreliable\n"); + if (!dtl_cache) return 0; - } for_each_possible_cpu(cpu) { pp = &paca[cpu]; @@ -334,10 +330,27 @@ static int alloc_dispatch_logs(void) return 0; } - -early_initcall(alloc_dispatch_logs); +#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ +static inline int alloc_dispatch_logs(void) +{ + return 0; +} #endif /* CONFIG_VIRT_CPU_ACCOUNTING */ +static int alloc_dispatch_log_kmem_cache(void) +{ + dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES, + DISPATCH_LOG_BYTES, 0, NULL); + if (!dtl_cache) { + pr_warn("Failed to create dispatch trace log buffer cache\n"); + pr_warn("Stolen time statistics will be unreliable\n"); + return 0; + } + + return alloc_dispatch_logs(); +} +early_initcall(alloc_dispatch_log_kmem_cache); + static void __init pSeries_setup_arch(void) { /* Discover PIC type and setup ppc_md accordingly */ diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 95f578158ff..fbffd7e47ab 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -207,7 +207,8 @@ static struct smp_ops_t pSeries_mpic_smp_ops = { }; static struct smp_ops_t pSeries_xics_smp_ops = { - .message_pass = NULL, /* Filled at runtime by xics_smp_probe() */ + .message_pass = smp_muxed_ipi_message_pass, + .cause_ipi = NULL, /* Filled at runtime by xics_smp_probe() */ .probe = xics_smp_probe, .kick_cpu = smp_pSeries_kick_cpu, .setup_cpu = smp_xics_setup_cpu, diff --git a/arch/powerpc/platforms/wsp/smp.c b/arch/powerpc/platforms/wsp/smp.c index c7b8db9ed9b..9d20fa9d371 100644 --- a/arch/powerpc/platforms/wsp/smp.c +++ b/arch/powerpc/platforms/wsp/smp.c @@ -75,7 +75,8 @@ static int __init smp_a2_probe(void) } static struct smp_ops_t a2_smp_ops = { - .message_pass = doorbell_message_pass, + .message_pass = smp_muxed_ipi_message_pass, + .cause_ipi = doorbell_cause_ipi, .probe = smp_a2_probe, .kick_cpu = smp_a2_kick_cpu, .setup_cpu = smp_a2_setup_cpu, diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 1636dd89670..bd0d54060b9 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -216,7 +216,7 @@ static int axon_ram_probe(struct platform_device *device) AXON_RAM_DEVICE_NAME, axon_ram_bank_id, bank->size >> 20); bank->ph_addr = resource.start; - bank->io_addr = (unsigned long) ioremap_flags( + bank->io_addr = (unsigned long) ioremap_prot( bank->ph_addr, bank->size, _PAGE_NO_CACHE); if (bank->io_addr == 0) { dev_err(&device->dev, "ioremap() failed\n"); diff --git a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c index 54fb1922fe3..11641589917 100644 --- a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c +++ b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c @@ -106,10 +106,10 @@ int __init instantiate_cache_sram(struct platform_device *dev, goto out_free; } - cache_sram->base_virt = ioremap_flags(cache_sram->base_phys, + cache_sram->base_virt = ioremap_prot(cache_sram->base_phys, cache_sram->size, _PAGE_COHERENT | PAGE_KERNEL); if (!cache_sram->base_virt) { - dev_err(&dev->dev, "%s: ioremap_flags failed\n", + dev_err(&dev->dev, "%s: ioremap_prot failed\n", dev->dev.of_node->full_name); ret = -ENOMEM; goto out_release; diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 01cd2f08951..92e78333c47 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -110,7 +110,7 @@ static void fsl_teardown_msi_irqs(struct pci_dev *pdev) list_for_each_entry(entry, &pdev->msi_list, list) { if (entry->irq == NO_IRQ) continue; - msi_data = irq_get_handler_data(entry->irq); + msi_data = irq_get_chip_data(entry->irq); irq_set_msi_desc(entry->irq, NULL); msi_bitmap_free_hwirqs(&msi_data->bitmap, virq_to_hw(entry->irq), 1); @@ -168,7 +168,7 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) rc = -ENOSPC; goto out_free; } - irq_set_handler_data(virq, msi_data); + /* chip_data is msi_data via host->hostdata in host->map() */ irq_set_msi_desc(virq, entry); fsl_compose_msi_msg(pdev, hwirq, &msg, msi_data); @@ -193,7 +193,7 @@ static void fsl_msi_cascade(unsigned int irq, struct irq_desc *desc) u32 have_shift = 0; struct fsl_msi_cascade_data *cascade_data; - cascade_data = (struct fsl_msi_cascade_data *)irq_get_handler_data(irq); + cascade_data = irq_get_handler_data(irq); msi_data = cascade_data->msi_data; raw_spin_lock(&desc->lock); @@ -253,7 +253,7 @@ unlock: static int fsl_of_msi_remove(struct platform_device *ofdev) { - struct fsl_msi *msi = ofdev->dev.platform_data; + struct fsl_msi *msi = platform_get_drvdata(ofdev); int virq, i; struct fsl_msi_cascade_data *cascade_data; @@ -330,7 +330,7 @@ static int __devinit fsl_of_msi_probe(struct platform_device *dev) dev_err(&dev->dev, "No memory for MSI structure\n"); return -ENOMEM; } - dev->dev.platform_data = msi; + platform_set_drvdata(dev, msi); msi->irqhost = irq_alloc_host(dev->dev.of_node, IRQ_HOST_MAP_LINEAR, NR_MSI_IRQS, &fsl_msi_host_ops, 0); diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c index 142770cb84b..d18bb27e4df 100644 --- a/arch/powerpc/sysdev/i8259.c +++ b/arch/powerpc/sysdev/i8259.c @@ -185,18 +185,6 @@ static int i8259_host_map(struct irq_host *h, unsigned int virq, return 0; } -static void i8259_host_unmap(struct irq_host *h, unsigned int virq) -{ - /* Make sure irq is masked in hardware */ - i8259_mask_irq(irq_get_irq_data(virq)); - - /* remove chip and handler */ - irq_set_chip_and_handler(virq, NULL, NULL); - - /* Make sure it's completed */ - synchronize_irq(virq); -} - static int i8259_host_xlate(struct irq_host *h, struct device_node *ct, const u32 *intspec, unsigned int intsize, irq_hw_number_t *out_hwirq, unsigned int *out_flags) @@ -220,7 +208,6 @@ static int i8259_host_xlate(struct irq_host *h, struct device_node *ct, static struct irq_host_ops i8259_host_ops = { .match = i8259_host_match, .map = i8259_host_map, - .unmap = i8259_host_unmap, .xlate = i8259_host_xlate, }; diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 0e47bce5f69..57e954142c7 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -663,7 +663,7 @@ static inline u32 mpic_physmask(u32 cpumask) int i; u32 mask = 0; - for (i = 0; i < NR_CPUS; ++i, cpumask >>= 1) + for (i = 0; i < min(32, NR_CPUS); ++i, cpumask >>= 1) mask |= (cpumask & 1) << get_hard_smp_processor_id(i); return mask; } @@ -872,16 +872,12 @@ int mpic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION), 1 << cpuid); } else { - cpumask_var_t tmp; + u32 mask = cpumask_bits(cpumask)[0]; - alloc_cpumask_var(&tmp, GFP_KERNEL); - - cpumask_and(tmp, cpumask, cpu_online_mask); + mask &= cpumask_bits(cpu_online_mask)[0]; mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION), - mpic_physmask(cpumask_bits(tmp)[0])); - - free_cpumask_var(tmp); + mpic_physmask(mask)); } return 0; @@ -1732,46 +1728,28 @@ void mpic_request_ipis(void) } } -static void mpic_send_ipi(unsigned int ipi_no, const struct cpumask *cpu_mask) +void smp_mpic_message_pass(int cpu, int msg) { struct mpic *mpic = mpic_primary; + u32 physmask; BUG_ON(mpic == NULL); -#ifdef DEBUG_IPI - DBG("%s: send_ipi(ipi_no: %d)\n", mpic->name, ipi_no); -#endif - - mpic_cpu_write(MPIC_INFO(CPU_IPI_DISPATCH_0) + - ipi_no * MPIC_INFO(CPU_IPI_DISPATCH_STRIDE), - mpic_physmask(cpumask_bits(cpu_mask)[0])); -} - -void smp_mpic_message_pass(int target, int msg) -{ - cpumask_var_t tmp; - /* make sure we're sending something that translates to an IPI */ if ((unsigned int)msg > 3) { printk("SMP %d: smp_message_pass: unknown msg %d\n", smp_processor_id(), msg); return; } - switch (target) { - case MSG_ALL: - mpic_send_ipi(msg, cpu_online_mask); - break; - case MSG_ALL_BUT_SELF: - alloc_cpumask_var(&tmp, GFP_NOWAIT); - cpumask_andnot(tmp, cpu_online_mask, - cpumask_of(smp_processor_id())); - mpic_send_ipi(msg, tmp); - free_cpumask_var(tmp); - break; - default: - mpic_send_ipi(msg, cpumask_of(target)); - break; - } + +#ifdef DEBUG_IPI + DBG("%s: send_ipi(ipi_no: %d)\n", mpic->name, msg); +#endif + + physmask = 1 << get_hard_smp_processor_id(cpu); + + mpic_cpu_write(MPIC_INFO(CPU_IPI_DISPATCH_0) + + msg * MPIC_INFO(CPU_IPI_DISPATCH_STRIDE), physmask); } int __init smp_mpic_probe(void) diff --git a/arch/powerpc/sysdev/xics/Kconfig b/arch/powerpc/sysdev/xics/Kconfig index 123b8ddf281..0031eda320c 100644 --- a/arch/powerpc/sysdev/xics/Kconfig +++ b/arch/powerpc/sysdev/xics/Kconfig @@ -1,5 +1,6 @@ config PPC_XICS def_bool n + select PPC_SMP_MUXED_IPI config PPC_ICP_NATIVE def_bool n diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index 76e87245bbf..9518d367a64 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -118,38 +118,18 @@ static void icp_hv_set_cpu_priority(unsigned char cppr) #ifdef CONFIG_SMP -static inline void icp_hv_do_message(int cpu, int msg) +static void icp_hv_cause_ipi(int cpu, unsigned long data) { - unsigned long *tgt = &per_cpu(xics_ipi_message, cpu); - - set_bit(msg, tgt); - mb(); icp_hv_set_qirr(cpu, IPI_PRIORITY); } -static void icp_hv_message_pass(int target, int msg) -{ - unsigned int i; - - if (target < NR_CPUS) { - icp_hv_do_message(target, msg); - } else { - for_each_online_cpu(i) { - if (target == MSG_ALL_BUT_SELF - && i == smp_processor_id()) - continue; - icp_hv_do_message(i, msg); - } - } -} - static irqreturn_t icp_hv_ipi_action(int irq, void *dev_id) { int cpu = smp_processor_id(); icp_hv_set_qirr(cpu, 0xff); - return xics_ipi_dispatch(cpu); + return smp_ipi_demux(); } #endif /* CONFIG_SMP */ @@ -162,7 +142,7 @@ static const struct icp_ops icp_hv_ops = { .flush_ipi = icp_hv_flush_ipi, #ifdef CONFIG_SMP .ipi_action = icp_hv_ipi_action, - .message_pass = icp_hv_message_pass, + .cause_ipi = icp_hv_cause_ipi, #endif }; diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c index 3508321c450..1f15ad43614 100644 --- a/arch/powerpc/sysdev/xics/icp-native.c +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -134,38 +134,18 @@ static unsigned int icp_native_get_irq(void) #ifdef CONFIG_SMP -static inline void icp_native_do_message(int cpu, int msg) +static void icp_native_cause_ipi(int cpu, unsigned long data) { - unsigned long *tgt = &per_cpu(xics_ipi_message, cpu); - - set_bit(msg, tgt); - mb(); icp_native_set_qirr(cpu, IPI_PRIORITY); } -static void icp_native_message_pass(int target, int msg) -{ - unsigned int i; - - if (target < NR_CPUS) { - icp_native_do_message(target, msg); - } else { - for_each_online_cpu(i) { - if (target == MSG_ALL_BUT_SELF - && i == smp_processor_id()) - continue; - icp_native_do_message(i, msg); - } - } -} - static irqreturn_t icp_native_ipi_action(int irq, void *dev_id) { int cpu = smp_processor_id(); icp_native_set_qirr(cpu, 0xff); - return xics_ipi_dispatch(cpu); + return smp_ipi_demux(); } #endif /* CONFIG_SMP */ @@ -283,7 +263,7 @@ static const struct icp_ops icp_native_ops = { .flush_ipi = icp_native_flush_ipi, #ifdef CONFIG_SMP .ipi_action = icp_native_ipi_action, - .message_pass = icp_native_message_pass, + .cause_ipi = icp_native_cause_ipi, #endif }; diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index a0576b705dd..445c5a01b76 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -126,32 +126,6 @@ void xics_mask_unknown_vec(unsigned int vec) #ifdef CONFIG_SMP -DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, xics_ipi_message); - -irqreturn_t xics_ipi_dispatch(int cpu) -{ - unsigned long *tgt = &per_cpu(xics_ipi_message, cpu); - - mb(); /* order mmio clearing qirr */ - while (*tgt) { - if (test_and_clear_bit(PPC_MSG_CALL_FUNCTION, tgt)) { - smp_message_recv(PPC_MSG_CALL_FUNCTION); - } - if (test_and_clear_bit(PPC_MSG_RESCHEDULE, tgt)) { - smp_message_recv(PPC_MSG_RESCHEDULE); - } - if (test_and_clear_bit(PPC_MSG_CALL_FUNC_SINGLE, tgt)) { - smp_message_recv(PPC_MSG_CALL_FUNC_SINGLE); - } -#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC) - if (test_and_clear_bit(PPC_MSG_DEBUGGER_BREAK, tgt)) { - smp_message_recv(PPC_MSG_DEBUGGER_BREAK); - } -#endif - } - return IRQ_HANDLED; -} - static void xics_request_ipi(void) { unsigned int ipi; @@ -161,17 +135,16 @@ static void xics_request_ipi(void) /* * IPIs are marked IRQF_DISABLED as they must run with irqs - * disabled + * disabled, and PERCPU. The handler was set in map. */ - irq_set_handler(ipi, handle_percpu_irq); BUG_ON(request_irq(ipi, icp_ops->ipi_action, IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL)); } int __init xics_smp_probe(void) { - /* Setup message_pass callback based on which ICP is used */ - smp_ops->message_pass = icp_ops->message_pass; + /* Setup cause_ipi callback based on which ICP is used */ + smp_ops->cause_ipi = icp_ops->cause_ipi; /* Register all the IPIs */ xics_request_ipi(); @@ -240,7 +213,7 @@ void xics_migrate_irqs_away(void) /* We can't set affinity on ISA interrupts */ if (virq < NUM_ISA_INTERRUPTS) continue; - if (virq_to_host(virq) != xics_host) + if (!virq_is_host(virq, xics_host)) continue; irq = (unsigned int)virq_to_hw(virq); /* We need to get IPIs still. */ @@ -367,15 +340,16 @@ static int xics_host_map(struct irq_host *h, unsigned int virq, /* Don't call into ICS for IPIs */ if (hw == XICS_IPI) { irq_set_chip_and_handler(virq, &xics_ipi_chip, - handle_fasteoi_irq); + handle_percpu_irq); return 0; } /* Let the ICS setup the chip data */ list_for_each_entry(ics, &ics_list, link) if (ics->map(ics, virq) == 0) - break; - return 0; + return 0; + + return -EINVAL; } static int xics_host_xlate(struct irq_host *h, struct device_node *ct, diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 91309c5c00d..42541bbcc7f 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -437,7 +437,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi) xmon_owner = cpu; mb(); if (ncpus > 1) { - smp_send_debugger_break(MSG_ALL_BUT_SELF); + smp_send_debugger_break(); /* wait for other cpus to come in */ for (timeout = 100000000; timeout != 0; --timeout) { if (cpumask_weight(&cpus_in_xmon) >= ncpus) diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 4e007c6a4b4..d80dcdee88f 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -481,5 +481,6 @@ source "drivers/misc/cb710/Kconfig" source "drivers/misc/iwmc3200top/Kconfig" source "drivers/misc/ti-st/Kconfig" source "drivers/misc/lis3lv02d/Kconfig" +source "drivers/misc/carma/Kconfig" endif # MISC_DEVICES diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index f5468602961..848e8464faa 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -44,3 +44,4 @@ obj-$(CONFIG_PCH_PHUB) += pch_phub.o obj-y += ti-st/ obj-$(CONFIG_AB8500_PWM) += ab8500-pwm.o obj-y += lis3lv02d/ +obj-y += carma/ diff --git a/drivers/misc/carma/Kconfig b/drivers/misc/carma/Kconfig new file mode 100644 index 00000000000..c90370ed712 --- /dev/null +++ b/drivers/misc/carma/Kconfig @@ -0,0 +1,17 @@ +config CARMA_FPGA + tristate "CARMA DATA-FPGA Access Driver" + depends on FSL_SOC && PPC_83xx && MEDIA_SUPPORT && HAS_DMA && FSL_DMA + select VIDEOBUF_DMA_SG + default n + help + Say Y here to include support for communicating with the data + processing FPGAs on the OVRO CARMA board. + +config CARMA_FPGA_PROGRAM + tristate "CARMA DATA-FPGA Programmer" + depends on FSL_SOC && PPC_83xx && MEDIA_SUPPORT && HAS_DMA && FSL_DMA + select VIDEOBUF_DMA_SG + default n + help + Say Y here to include support for programming the data processing + FPGAs on the OVRO CARMA board. diff --git a/drivers/misc/carma/Makefile b/drivers/misc/carma/Makefile new file mode 100644 index 00000000000..ff36ac2ce53 --- /dev/null +++ b/drivers/misc/carma/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_CARMA_FPGA) += carma-fpga.o +obj-$(CONFIG_CARMA_FPGA_PROGRAM) += carma-fpga-program.o diff --git a/drivers/misc/carma/carma-fpga-program.c b/drivers/misc/carma/carma-fpga-program.c new file mode 100644 index 00000000000..7ce6065dc20 --- /dev/null +++ b/drivers/misc/carma/carma-fpga-program.c @@ -0,0 +1,1141 @@ +/* + * CARMA Board DATA-FPGA Programmer + * + * Copyright (c) 2009-2011 Ira W. Snyder <iws@ovro.caltech.edu> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/dma-mapping.h> +#include <linux/of_platform.h> +#include <linux/completion.h> +#include <linux/miscdevice.h> +#include <linux/dmaengine.h> +#include <linux/interrupt.h> +#include <linux/highmem.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/leds.h> +#include <linux/slab.h> +#include <linux/kref.h> +#include <linux/fs.h> +#include <linux/io.h> + +#include <media/videobuf-dma-sg.h> + +/* MPC8349EMDS specific get_immrbase() */ +#include <sysdev/fsl_soc.h> + +static const char drv_name[] = "carma-fpga-program"; + +/* + * Firmware images are always this exact size + * + * 12849552 bytes for a CARMA Digitizer Board (EP2S90 FPGAs) + * 18662880 bytes for a CARMA Correlator Board (EP2S130 FPGAs) + */ +#define FW_SIZE_EP2S90 12849552 +#define FW_SIZE_EP2S130 18662880 + +struct fpga_dev { + struct miscdevice miscdev; + + /* Reference count */ + struct kref ref; + + /* Device Registers */ + struct device *dev; + void __iomem *regs; + void __iomem *immr; + + /* Freescale DMA Device */ + struct dma_chan *chan; + + /* Interrupts */ + int irq, status; + struct completion completion; + + /* FPGA Bitfile */ + struct mutex lock; + + struct videobuf_dmabuf vb; + bool vb_allocated; + + /* max size and written bytes */ + size_t fw_size; + size_t bytes; +}; + +/* + * FPGA Bitfile Helpers + */ + +/** + * fpga_drop_firmware_data() - drop the bitfile image from memory + * @priv: the driver's private data structure + * + * LOCKING: must hold priv->lock + */ +static void fpga_drop_firmware_data(struct fpga_dev *priv) +{ + videobuf_dma_free(&priv->vb); + priv->vb_allocated = false; + priv->bytes = 0; +} + +/* + * Private Data Reference Count + */ + +static void fpga_dev_remove(struct kref *ref) +{ + struct fpga_dev *priv = container_of(ref, struct fpga_dev, ref); + + /* free any firmware image that was not programmed */ + fpga_drop_firmware_data(priv); + + mutex_destroy(&priv->lock); + kfree(priv); +} + +/* + * LED Trigger (could be a seperate module) + */ + +/* + * NOTE: this whole thing does have the problem that whenever the led's are + * NOTE: first set to use the fpga trigger, they could be in the wrong state + */ + +DEFINE_LED_TRIGGER(ledtrig_fpga); + +static void ledtrig_fpga_programmed(bool enabled) +{ + if (enabled) + led_trigger_event(ledtrig_fpga, LED_FULL); + else + led_trigger_event(ledtrig_fpga, LED_OFF); +} + +/* + * FPGA Register Helpers + */ + +/* Register Definitions */ +#define FPGA_CONFIG_CONTROL 0x40 +#define FPGA_CONFIG_STATUS 0x44 +#define FPGA_CONFIG_FIFO_SIZE 0x48 +#define FPGA_CONFIG_FIFO_USED 0x4C +#define FPGA_CONFIG_TOTAL_BYTE_COUNT 0x50 +#define FPGA_CONFIG_CUR_BYTE_COUNT 0x54 + +#define FPGA_FIFO_ADDRESS 0x3000 + +static int fpga_fifo_size(void __iomem *regs) +{ + return ioread32be(regs + FPGA_CONFIG_FIFO_SIZE); +} + +#define CFG_STATUS_ERR_MASK 0xfffe + +static int fpga_config_error(void __iomem *regs) +{ + return ioread32be(regs + FPGA_CONFIG_STATUS) & CFG_STATUS_ERR_MASK; +} + +static int fpga_fifo_empty(void __iomem *regs) +{ + return ioread32be(regs + FPGA_CONFIG_FIFO_USED) == 0; +} + +static void fpga_fifo_write(void __iomem *regs, u32 val) +{ + iowrite32be(val, regs + FPGA_FIFO_ADDRESS); +} + +static void fpga_set_byte_count(void __iomem *regs, u32 count) +{ + iowrite32be(count, regs + FPGA_CONFIG_TOTAL_BYTE_COUNT); +} + +#define CFG_CTL_ENABLE (1 << 0) +#define CFG_CTL_RESET (1 << 1) +#define CFG_CTL_DMA (1 << 2) + +static void fpga_programmer_enable(struct fpga_dev *priv, bool dma) +{ + u32 val; + + val = (dma) ? (CFG_CTL_ENABLE | CFG_CTL_DMA) : CFG_CTL_ENABLE; + iowrite32be(val, priv->regs + FPGA_CONFIG_CONTROL); +} + +static void fpga_programmer_disable(struct fpga_dev *priv) +{ + iowrite32be(0x0, priv->regs + FPGA_CONFIG_CONTROL); +} + +static void fpga_dump_registers(struct fpga_dev *priv) +{ + u32 control, status, size, used, total, curr; + + /* good status: do nothing */ + if (priv->status == 0) + return; + + /* Dump all status registers */ + control = ioread32be(priv->regs + FPGA_CONFIG_CONTROL); + status = ioread32be(priv->regs + FPGA_CONFIG_STATUS); + size = ioread32be(priv->regs + FPGA_CONFIG_FIFO_SIZE); + used = ioread32be(priv->regs + FPGA_CONFIG_FIFO_USED); + total = ioread32be(priv->regs + FPGA_CONFIG_TOTAL_BYTE_COUNT); + curr = ioread32be(priv->regs + FPGA_CONFIG_CUR_BYTE_COUNT); + + dev_err(priv->dev, "Configuration failed, dumping status registers\n"); + dev_err(priv->dev, "Control: 0x%.8x\n", control); + dev_err(priv->dev, "Status: 0x%.8x\n", status); + dev_err(priv->dev, "FIFO Size: 0x%.8x\n", size); + dev_err(priv->dev, "FIFO Used: 0x%.8x\n", used); + dev_err(priv->dev, "FIFO Total: 0x%.8x\n", total); + dev_err(priv->dev, "FIFO Curr: 0x%.8x\n", curr); +} + +/* + * FPGA Power Supply Code + */ + +#define CTL_PWR_CONTROL 0x2006 +#define CTL_PWR_STATUS 0x200A +#define CTL_PWR_FAIL 0x200B + +#define PWR_CONTROL_ENABLE 0x01 + +#define PWR_STATUS_ERROR_MASK 0x10 +#define PWR_STATUS_GOOD 0x0f + +/* + * Determine if the FPGA power is good for all supplies + */ +static bool fpga_power_good(struct fpga_dev *priv) +{ + u8 val; + + val = ioread8(priv->regs + CTL_PWR_STATUS); + if (val & PWR_STATUS_ERROR_MASK) + return false; + + return val == PWR_STATUS_GOOD; +} + +/* + * Disable the FPGA power supplies + */ +static void fpga_disable_power_supplies(struct fpga_dev *priv) +{ + unsigned long start; + u8 val; + + iowrite8(0x0, priv->regs + CTL_PWR_CONTROL); + + /* + * Wait 500ms for the power rails to discharge + * + * Without this delay, the CTL-CPLD state machine can get into a + * state where it is waiting for the power-goods to assert, but they + * never do. This only happens when enabling and disabling the + * power sequencer very rapidly. + * + * The loop below will also wait for the power goods to de-assert, + * but testing has shown that they are always disabled by the time + * the sleep completes. However, omitting the sleep and only waiting + * for the power-goods to de-assert was not sufficient to ensure + * that the power sequencer would not wedge itself. + */ + msleep(500); + + start = jiffies; + while (time_before(jiffies, start + HZ)) { + val = ioread8(priv->regs + CTL_PWR_STATUS); + if (!(val & PWR_STATUS_GOOD)) + break; + + usleep_range(5000, 10000); + } + + val = ioread8(priv->regs + CTL_PWR_STATUS); + if (val & PWR_STATUS_GOOD) { + dev_err(priv->dev, "power disable failed: " + "power goods: status 0x%.2x\n", val); + } + + if (val & PWR_STATUS_ERROR_MASK) { + dev_err(priv->dev, "power disable failed: " + "alarm bit set: status 0x%.2x\n", val); + } +} + +/** + * fpga_enable_power_supplies() - enable the DATA-FPGA power supplies + * @priv: the driver's private data structure + * + * Enable the DATA-FPGA power supplies, waiting up to 1 second for + * them to enable successfully. + * + * Returns 0 on success, -ERRNO otherwise + */ +static int fpga_enable_power_supplies(struct fpga_dev *priv) +{ + unsigned long start = jiffies; + + if (fpga_power_good(priv)) { + dev_dbg(priv->dev, "power was already good\n"); + return 0; + } + + iowrite8(PWR_CONTROL_ENABLE, priv->regs + CTL_PWR_CONTROL); + while (time_before(jiffies, start + HZ)) { + if (fpga_power_good(priv)) + return 0; + + usleep_range(5000, 10000); + } + + return fpga_power_good(priv) ? 0 : -ETIMEDOUT; +} + +/* + * Determine if the FPGA power supplies are all enabled + */ +static bool fpga_power_enabled(struct fpga_dev *priv) +{ + u8 val; + + val = ioread8(priv->regs + CTL_PWR_CONTROL); + if (val & PWR_CONTROL_ENABLE) + return true; + + return false; +} + +/* + * Determine if the FPGA's are programmed and running correctly + */ +static bool fpga_running(struct fpga_dev *priv) +{ + if (!fpga_power_good(priv)) + return false; + + /* Check the config done bit */ + return ioread32be(priv->regs + FPGA_CONFIG_STATUS) & (1 << 18); +} + +/* + * FPGA Programming Code + */ + +/** + * fpga_program_block() - put a block of data into the programmer's FIFO + * @priv: the driver's private data structure + * @buf: the data to program + * @count: the length of data to program (must be a multiple of 4 bytes) + * + * Returns 0 on success, -ERRNO otherwise + */ +static int fpga_program_block(struct fpga_dev *priv, void *buf, size_t count) +{ + u32 *data = buf; + int size = fpga_fifo_size(priv->regs); + int i, len; + unsigned long timeout; + + /* enforce correct data length for the FIFO */ + BUG_ON(count % 4 != 0); + + while (count > 0) { + + /* Get the size of the block to write (maximum is FIFO_SIZE) */ + len = min_t(size_t, count, size); + timeout = jiffies + HZ / 4; + + /* Write the block */ + for (i = 0; i < len / 4; i++) + fpga_fifo_write(priv->regs, data[i]); + + /* Update the amounts left */ + count -= len; + data += len / 4; + + /* Wait for the fifo to empty */ + while (true) { + + if (fpga_fifo_empty(priv->regs)) { + break; + } else { + dev_dbg(priv->dev, "Fifo not empty\n"); + cpu_relax(); + } + + if (fpga_config_error(priv->regs)) { + dev_err(priv->dev, "Error detected\n"); + return -EIO; + } + + if (time_after(jiffies, timeout)) { + dev_err(priv->dev, "Fifo drain timeout\n"); + return -ETIMEDOUT; + } + + usleep_range(5000, 10000); + } + } + + return 0; +} + +/** + * fpga_program_cpu() - program the DATA-FPGA's using the CPU + * @priv: the driver's private data structure + * + * This is useful when the DMA programming method fails. It is possible to + * wedge the Freescale DMA controller such that the DMA programming method + * always fails. This method has always succeeded. + * + * Returns 0 on success, -ERRNO otherwise + */ +static noinline int fpga_program_cpu(struct fpga_dev *priv) +{ + int ret; + + /* Disable the programmer */ + fpga_programmer_disable(priv); + + /* Set the total byte count */ + fpga_set_byte_count(priv->regs, priv->bytes); + dev_dbg(priv->dev, "total byte count %u bytes\n", priv->bytes); + + /* Enable the controller for programming */ + fpga_programmer_enable(priv, false); + dev_dbg(priv->dev, "enabled the controller\n"); + + /* Write each chunk of the FPGA bitfile to FPGA programmer */ + ret = fpga_program_block(priv, priv->vb.vaddr, priv->bytes); + if (ret) + goto out_disable_controller; + + /* Wait for the interrupt handler to signal that programming finished */ + ret = wait_for_completion_timeout(&priv->completion, 2 * HZ); + if (!ret) { + dev_err(priv->dev, "Timed out waiting for completion\n"); + ret = -ETIMEDOUT; + goto out_disable_controller; + } + + /* Retrieve the status from the interrupt handler */ + ret = priv->status; + +out_disable_controller: + fpga_programmer_disable(priv); + return ret; +} + +#define FIFO_DMA_ADDRESS 0xf0003000 +#define FIFO_MAX_LEN 4096 + +/** + * fpga_program_dma() - program the DATA-FPGA's using the DMA engine + * @priv: the driver's private data structure + * + * Program the DATA-FPGA's using the Freescale DMA engine. This requires that + * the engine is programmed such that the hardware DMA request lines can + * control the entire DMA transaction. The system controller FPGA then + * completely offloads the programming from the CPU. + * + * Returns 0 on success, -ERRNO otherwise + */ +static noinline int fpga_program_dma(struct fpga_dev *priv) +{ + struct videobuf_dmabuf *vb = &priv->vb; + struct dma_chan *chan = priv->chan; + struct dma_async_tx_descriptor *tx; + size_t num_pages, len, avail = 0; + struct dma_slave_config config; + struct scatterlist *sg; + struct sg_table table; + dma_cookie_t cookie; + int ret, i; + + /* Disable the programmer */ + fpga_programmer_disable(priv); + + /* Allocate a scatterlist for the DMA destination */ + num_pages = DIV_ROUND_UP(priv->bytes, FIFO_MAX_LEN); + ret = sg_alloc_table(&table, num_pages, GFP_KERNEL); + if (ret) { + dev_err(priv->dev, "Unable to allocate dst scatterlist\n"); + ret = -ENOMEM; + goto out_return; + } + + /* + * This is an ugly hack + * + * We fill in a scatterlist as if it were mapped for DMA. This is + * necessary because there exists no better structure for this + * inside the kernel code. + * + * As an added bonus, we can use the DMAEngine API for all of this, + * rather than inventing another extremely similar API. + */ + avail = priv->bytes; + for_each_sg(table.sgl, sg, num_pages, i) { + len = min_t(size_t, avail, FIFO_MAX_LEN); + sg_dma_address(sg) = FIFO_DMA_ADDRESS; + sg_dma_len(sg) = len; + + avail -= len; + } + + /* Map the buffer for DMA */ + ret = videobuf_dma_map(priv->dev, &priv->vb); + if (ret) { + dev_err(priv->dev, "Unable to map buffer for DMA\n"); + goto out_free_table; + } + + /* + * Configure the DMA channel to transfer FIFO_SIZE / 2 bytes per + * transaction, and then put it under external control + */ + memset(&config, 0, sizeof(config)); + config.direction = DMA_TO_DEVICE; + config.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; + config.dst_maxburst = fpga_fifo_size(priv->regs) / 2 / 4; + ret = chan->device->device_control(chan, DMA_SLAVE_CONFIG, + (unsigned long)&config); + if (ret) { + dev_err(priv->dev, "DMA slave configuration failed\n"); + goto out_dma_unmap; + } + + ret = chan->device->device_control(chan, FSLDMA_EXTERNAL_START, 1); + if (ret) { + dev_err(priv->dev, "DMA external control setup failed\n"); + goto out_dma_unmap; + } + + /* setup and submit the DMA transaction */ + tx = chan->device->device_prep_dma_sg(chan, + table.sgl, num_pages, + vb->sglist, vb->sglen, 0); + if (!tx) { + dev_err(priv->dev, "Unable to prep DMA transaction\n"); + ret = -ENOMEM; + goto out_dma_unmap; + } + + cookie = tx->tx_submit(tx); + if (dma_submit_error(cookie)) { + dev_err(priv->dev, "Unable to submit DMA transaction\n"); + ret = -ENOMEM; + goto out_dma_unmap; + } + + dma_async_memcpy_issue_pending(chan); + + /* Set the total byte count */ + fpga_set_byte_count(priv->regs, priv->bytes); + dev_dbg(priv->dev, "total byte count %u bytes\n", priv->bytes); + + /* Enable the controller for DMA programming */ + fpga_programmer_enable(priv, true); + dev_dbg(priv->dev, "enabled the controller\n"); + + /* Wait for the interrupt handler to signal that programming finished */ + ret = wait_for_completion_timeout(&priv->completion, 2 * HZ); + if (!ret) { + dev_err(priv->dev, "Timed out waiting for completion\n"); + ret = -ETIMEDOUT; + goto out_disable_controller; + } + + /* Retrieve the status from the interrupt handler */ + ret = priv->status; + +out_disable_controller: + fpga_programmer_disable(priv); +out_dma_unmap: + videobuf_dma_unmap(priv->dev, vb); +out_free_table: + sg_free_table(&table); +out_return: + return ret; +} + +/* + * Interrupt Handling + */ + +static irqreturn_t fpga_irq(int irq, void *dev_id) +{ + struct fpga_dev *priv = dev_id; + + /* Save the status */ + priv->status = fpga_config_error(priv->regs) ? -EIO : 0; + dev_dbg(priv->dev, "INTERRUPT status %d\n", priv->status); + fpga_dump_registers(priv); + + /* Disabling the programmer clears the interrupt */ + fpga_programmer_disable(priv); + + /* Notify any waiters */ + complete(&priv->completion); + + return IRQ_HANDLED; +} + +/* + * SYSFS Helpers + */ + +/** + * fpga_do_stop() - deconfigure (reset) the DATA-FPGA's + * @priv: the driver's private data structure + * + * LOCKING: must hold priv->lock + */ +static int fpga_do_stop(struct fpga_dev *priv) +{ + u32 val; + + /* Set the led to unprogrammed */ + ledtrig_fpga_programmed(false); + + /* Pulse the config line to reset the FPGA's */ + val = CFG_CTL_ENABLE | CFG_CTL_RESET; + iowrite32be(val, priv->regs + FPGA_CONFIG_CONTROL); + iowrite32be(0x0, priv->regs + FPGA_CONFIG_CONTROL); + + return 0; +} + +static noinline int fpga_do_program(struct fpga_dev *priv) +{ + int ret; + + if (priv->bytes != priv->fw_size) { + dev_err(priv->dev, "Incorrect bitfile size: got %zu bytes, " + "should be %zu bytes\n", + priv->bytes, priv->fw_size); + return -EINVAL; + } + + if (!fpga_power_enabled(priv)) { + dev_err(priv->dev, "Power not enabled\n"); + return -EINVAL; + } + + if (!fpga_power_good(priv)) { + dev_err(priv->dev, "Power not good\n"); + return -EINVAL; + } + + /* Set the LED to unprogrammed */ + ledtrig_fpga_programmed(false); + + /* Try to program the FPGA's using DMA */ + ret = fpga_program_dma(priv); + + /* If DMA failed or doesn't exist, try with CPU */ + if (ret) { + dev_warn(priv->dev, "Falling back to CPU programming\n"); + ret = fpga_program_cpu(priv); + } + + if (ret) { + dev_err(priv->dev, "Unable to program FPGA's\n"); + return ret; + } + + /* Drop the firmware bitfile from memory */ + fpga_drop_firmware_data(priv); + + dev_dbg(priv->dev, "FPGA programming successful\n"); + ledtrig_fpga_programmed(true); + + return 0; +} + +/* + * File Operations + */ + +static int fpga_open(struct inode *inode, struct file *filp) +{ + /* + * The miscdevice layer puts our struct miscdevice into the + * filp->private_data field. We use this to find our private + * data and then overwrite it with our own private structure. + */ + struct fpga_dev *priv = container_of(filp->private_data, + struct fpga_dev, miscdev); + unsigned int nr_pages; + int ret; + + /* We only allow one process at a time */ + ret = mutex_lock_interruptible(&priv->lock); + if (ret) + return ret; + + filp->private_data = priv; + kref_get(&priv->ref); + + /* Truncation: drop any existing data */ + if (filp->f_flags & O_TRUNC) + priv->bytes = 0; + + /* Check if we have already allocated a buffer */ + if (priv->vb_allocated) + return 0; + + /* Allocate a buffer to hold enough data for the bitfile */ + nr_pages = DIV_ROUND_UP(priv->fw_size, PAGE_SIZE); + ret = videobuf_dma_init_kernel(&priv->vb, DMA_TO_DEVICE, nr_pages); + if (ret) { + dev_err(priv->dev, "unable to allocate data buffer\n"); + mutex_unlock(&priv->lock); + kref_put(&priv->ref, fpga_dev_remove); + return ret; + } + + priv->vb_allocated = true; + return 0; +} + +static int fpga_release(struct inode *inode, struct file *filp) +{ + struct fpga_dev *priv = filp->private_data; + + mutex_unlock(&priv->lock); + kref_put(&priv->ref, fpga_dev_remove); + return 0; +} + +static ssize_t fpga_write(struct file *filp, const char __user *buf, + size_t count, loff_t *f_pos) +{ + struct fpga_dev *priv = filp->private_data; + + /* FPGA bitfiles have an exact size: disallow anything else */ + if (priv->bytes >= priv->fw_size) + return -ENOSPC; + + count = min_t(size_t, priv->fw_size - priv->bytes, count); + if (copy_from_user(priv->vb.vaddr + priv->bytes, buf, count)) + return -EFAULT; + + priv->bytes += count; + return count; +} + +static ssize_t fpga_read(struct file *filp, char __user *buf, size_t count, + loff_t *f_pos) +{ + struct fpga_dev *priv = filp->private_data; + + count = min_t(size_t, priv->bytes - *f_pos, count); + if (copy_to_user(buf, priv->vb.vaddr + *f_pos, count)) + return -EFAULT; + + *f_pos += count; + return count; +} + +static loff_t fpga_llseek(struct file *filp, loff_t offset, int origin) +{ + struct fpga_dev *priv = filp->private_data; + loff_t newpos; + + /* only read-only opens are allowed to seek */ + if ((filp->f_flags & O_ACCMODE) != O_RDONLY) + return -EINVAL; + + switch (origin) { + case SEEK_SET: /* seek relative to the beginning of the file */ + newpos = offset; + break; + case SEEK_CUR: /* seek relative to current position in the file */ + newpos = filp->f_pos + offset; + break; + case SEEK_END: /* seek relative to the end of the file */ + newpos = priv->fw_size - offset; + break; + default: + return -EINVAL; + } + + /* check for sanity */ + if (newpos > priv->fw_size) + return -EINVAL; + + filp->f_pos = newpos; + return newpos; +} + +static const struct file_operations fpga_fops = { + .open = fpga_open, + .release = fpga_release, + .write = fpga_write, + .read = fpga_read, + .llseek = fpga_llseek, +}; + +/* + * Device Attributes + */ + +static ssize_t pfail_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + u8 val; + + val = ioread8(priv->regs + CTL_PWR_FAIL); + return snprintf(buf, PAGE_SIZE, "0x%.2x\n", val); +} + +static ssize_t pgood_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + return snprintf(buf, PAGE_SIZE, "%d\n", fpga_power_good(priv)); +} + +static ssize_t penable_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + return snprintf(buf, PAGE_SIZE, "%d\n", fpga_power_enabled(priv)); +} + +static ssize_t penable_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + unsigned long val; + int ret; + + if (strict_strtoul(buf, 0, &val)) + return -EINVAL; + + if (val) { + ret = fpga_enable_power_supplies(priv); + if (ret) + return ret; + } else { + fpga_do_stop(priv); + fpga_disable_power_supplies(priv); + } + + return count; +} + +static ssize_t program_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + return snprintf(buf, PAGE_SIZE, "%d\n", fpga_running(priv)); +} + +static ssize_t program_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct fpga_dev *priv = dev_get_drvdata(dev); + unsigned long val; + int ret; + + if (strict_strtoul(buf, 0, &val)) + return -EINVAL; + + /* We can't have an image writer and be programming simultaneously */ + if (mutex_lock_interruptible(&priv->lock)) + return -ERESTARTSYS; + + /* Program or Reset the FPGA's */ + ret = val ? fpga_do_program(priv) : fpga_do_stop(priv); + if (ret) + goto out_unlock; + + /* Success */ + ret = count; + +out_unlock: + mutex_unlock(&priv->lock); + return ret; +} + +static DEVICE_ATTR(power_fail, S_IRUGO, pfail_show, NULL); +static DEVICE_ATTR(power_good, S_IRUGO, pgood_show, NULL); +static DEVICE_ATTR(power_enable, S_IRUGO | S_IWUSR, + penable_show, penable_store); + +static DEVICE_ATTR(program, S_IRUGO | S_IWUSR, + program_show, program_store); + +static struct attribute *fpga_attributes[] = { + &dev_attr_power_fail.attr, + &dev_attr_power_good.attr, + &dev_attr_power_enable.attr, + &dev_attr_program.attr, + NULL, +}; + +static const struct attribute_group fpga_attr_group = { + .attrs = fpga_attributes, +}; + +/* + * OpenFirmware Device Subsystem + */ + +#define SYS_REG_VERSION 0x00 +#define SYS_REG_GEOGRAPHIC 0x10 + +static bool dma_filter(struct dma_chan *chan, void *data) +{ + /* + * DMA Channel #0 is the only acceptable device + * + * This probably won't survive an unload/load cycle of the Freescale + * DMAEngine driver, but that won't be a problem + */ + return chan->chan_id == 0 && chan->device->dev_id == 0; +} + +static int fpga_of_remove(struct platform_device *op) +{ + struct fpga_dev *priv = dev_get_drvdata(&op->dev); + struct device *this_device = priv->miscdev.this_device; + + sysfs_remove_group(&this_device->kobj, &fpga_attr_group); + misc_deregister(&priv->miscdev); + + free_irq(priv->irq, priv); + irq_dispose_mapping(priv->irq); + + /* make sure the power supplies are off */ + fpga_disable_power_supplies(priv); + + /* unmap registers */ + iounmap(priv->immr); + iounmap(priv->regs); + + dma_release_channel(priv->chan); + + /* drop our reference to the private data structure */ + kref_put(&priv->ref, fpga_dev_remove); + return 0; +} + +/* CTL-CPLD Version Register */ +#define CTL_CPLD_VERSION 0x2000 + +static int fpga_of_probe(struct platform_device *op, + const struct of_device_id *match) +{ + struct device_node *of_node = op->dev.of_node; + struct device *this_device; + struct fpga_dev *priv; + dma_cap_mask_t mask; + u32 ver; + int ret; + + /* Allocate private data */ + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { + dev_err(&op->dev, "Unable to allocate private data\n"); + ret = -ENOMEM; + goto out_return; + } + + /* Setup the miscdevice */ + priv->miscdev.minor = MISC_DYNAMIC_MINOR; + priv->miscdev.name = drv_name; + priv->miscdev.fops = &fpga_fops; + + kref_init(&priv->ref); + + dev_set_drvdata(&op->dev, priv); + priv->dev = &op->dev; + mutex_init(&priv->lock); + init_completion(&priv->completion); + videobuf_dma_init(&priv->vb); + + dev_set_drvdata(priv->dev, priv); + dma_cap_zero(mask); + dma_cap_set(DMA_MEMCPY, mask); + dma_cap_set(DMA_INTERRUPT, mask); + dma_cap_set(DMA_SLAVE, mask); + dma_cap_set(DMA_SG, mask); + + /* Get control of DMA channel #0 */ + priv->chan = dma_request_channel(mask, dma_filter, NULL); + if (!priv->chan) { + dev_err(&op->dev, "Unable to acquire DMA channel #0\n"); + ret = -ENODEV; + goto out_free_priv; + } + + /* Remap the registers for use */ + priv->regs = of_iomap(of_node, 0); + if (!priv->regs) { + dev_err(&op->dev, "Unable to ioremap registers\n"); + ret = -ENOMEM; + goto out_dma_release_channel; + } + + /* Remap the IMMR for use */ + priv->immr = ioremap(get_immrbase(), 0x100000); + if (!priv->immr) { + dev_err(&op->dev, "Unable to ioremap IMMR\n"); + ret = -ENOMEM; + goto out_unmap_regs; + } + + /* + * Check that external DMA is configured + * + * U-Boot does this for us, but we should check it and bail out if + * there is a problem. Failing to have this register setup correctly + * will cause the DMA controller to transfer a single cacheline + * worth of data, then wedge itself. + */ + if ((ioread32be(priv->immr + 0x114) & 0xE00) != 0xE00) { + dev_err(&op->dev, "External DMA control not configured\n"); + ret = -ENODEV; + goto out_unmap_immr; + } + + /* + * Check the CTL-CPLD version + * + * This driver uses the CTL-CPLD DATA-FPGA power sequencer, and we + * don't want to run on any version of the CTL-CPLD that does not use + * a compatible register layout. + * + * v2: changed register layout, added power sequencer + * v3: added glitch filter on the i2c overcurrent/overtemp outputs + */ + ver = ioread8(priv->regs + CTL_CPLD_VERSION); + if (ver != 0x02 && ver != 0x03) { + dev_err(&op->dev, "CTL-CPLD is not version 0x02 or 0x03!\n"); + ret = -ENODEV; + goto out_unmap_immr; + } + + /* Set the exact size that the firmware image should be */ + ver = ioread32be(priv->regs + SYS_REG_VERSION); + priv->fw_size = (ver & (1 << 18)) ? FW_SIZE_EP2S130 : FW_SIZE_EP2S90; + + /* Find the correct IRQ number */ + priv->irq = irq_of_parse_and_map(of_node, 0); + if (priv->irq == NO_IRQ) { + dev_err(&op->dev, "Unable to find IRQ line\n"); + ret = -ENODEV; + goto out_unmap_immr; + } + + /* Request the IRQ */ + ret = request_irq(priv->irq, fpga_irq, IRQF_SHARED, drv_name, priv); + if (ret) { + dev_err(&op->dev, "Unable to request IRQ %d\n", priv->irq); + ret = -ENODEV; + goto out_irq_dispose_mapping; + } + + /* Reset and stop the FPGA's, just in case */ + fpga_do_stop(priv); + + /* Register the miscdevice */ + ret = misc_register(&priv->miscdev); + if (ret) { + dev_err(&op->dev, "Unable to register miscdevice\n"); + goto out_free_irq; + } + + /* Create the sysfs files */ + this_device = priv->miscdev.this_device; + dev_set_drvdata(this_device, priv); + ret = sysfs_create_group(&this_device->kobj, &fpga_attr_group); + if (ret) { + dev_err(&op->dev, "Unable to create sysfs files\n"); + goto out_misc_deregister; + } + + dev_info(priv->dev, "CARMA FPGA Programmer: %s rev%s with %s FPGAs\n", + (ver & (1 << 17)) ? "Correlator" : "Digitizer", + (ver & (1 << 16)) ? "B" : "A", + (ver & (1 << 18)) ? "EP2S130" : "EP2S90"); + + return 0; + +out_misc_deregister: + misc_deregister(&priv->miscdev); +out_free_irq: + free_irq(priv->irq, priv); +out_irq_dispose_mapping: + irq_dispose_mapping(priv->irq); +out_unmap_immr: + iounmap(priv->immr); +out_unmap_regs: + iounmap(priv->regs); +out_dma_release_channel: + dma_release_channel(priv->chan); +out_free_priv: + kref_put(&priv->ref, fpga_dev_remove); +out_return: + return ret; +} + +static struct of_device_id fpga_of_match[] = { + { .compatible = "carma,fpga-programmer", }, + {}, +}; + +static struct of_platform_driver fpga_of_driver = { + .probe = fpga_of_probe, + .remove = fpga_of_remove, + .driver = { + .name = drv_name, + .of_match_table = fpga_of_match, + .owner = THIS_MODULE, + }, +}; + +/* + * Module Init / Exit + */ + +static int __init fpga_init(void) +{ + led_trigger_register_simple("fpga", &ledtrig_fpga); + return of_register_platform_driver(&fpga_of_driver); +} + +static void __exit fpga_exit(void) +{ + of_unregister_platform_driver(&fpga_of_driver); + led_trigger_unregister_simple(ledtrig_fpga); +} + +MODULE_AUTHOR("Ira W. Snyder <iws@ovro.caltech.edu>"); +MODULE_DESCRIPTION("CARMA Board DATA-FPGA Programmer"); +MODULE_LICENSE("GPL"); + +module_init(fpga_init); +module_exit(fpga_exit); diff --git a/drivers/misc/carma/carma-fpga.c b/drivers/misc/carma/carma-fpga.c new file mode 100644 index 00000000000..3965821fef1 --- /dev/null +++ b/drivers/misc/carma/carma-fpga.c @@ -0,0 +1,1433 @@ +/* + * CARMA DATA-FPGA Access Driver + * + * Copyright (c) 2009-2011 Ira W. Snyder <iws@ovro.caltech.edu> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +/* + * FPGA Memory Dump Format + * + * FPGA #0 control registers (32 x 32-bit words) + * FPGA #1 control registers (32 x 32-bit words) + * FPGA #2 control registers (32 x 32-bit words) + * FPGA #3 control registers (32 x 32-bit words) + * SYSFPGA control registers (32 x 32-bit words) + * FPGA #0 correlation array (NUM_CORL0 correlation blocks) + * FPGA #1 correlation array (NUM_CORL1 correlation blocks) + * FPGA #2 correlation array (NUM_CORL2 correlation blocks) + * FPGA #3 correlation array (NUM_CORL3 correlation blocks) + * + * Each correlation array consists of: + * + * Correlation Data (2 x NUM_LAGSn x 32-bit words) + * Pipeline Metadata (2 x NUM_METAn x 32-bit words) + * Quantization Counters (2 x NUM_QCNTn x 32-bit words) + * + * The NUM_CORLn, NUM_LAGSn, NUM_METAn, and NUM_QCNTn values come from + * the FPGA configuration registers. They do not change once the FPGA's + * have been programmed, they only change on re-programming. + */ + +/* + * Basic Description: + * + * This driver is used to capture correlation spectra off of the four data + * processing FPGAs. The FPGAs are often reprogrammed at runtime, therefore + * this driver supports dynamic enable/disable of capture while the device + * remains open. + * + * The nominal capture rate is 64Hz (every 15.625ms). To facilitate this fast + * capture rate, all buffers are pre-allocated to avoid any potentially long + * running memory allocations while capturing. + * + * There are two lists and one pointer which are used to keep track of the + * different states of data buffers. + * + * 1) free list + * This list holds all empty data buffers which are ready to receive data. + * + * 2) inflight pointer + * This pointer holds the currently inflight data buffer. This buffer is having + * data copied into it by the DMA engine. + * + * 3) used list + * This list holds data buffers which have been filled, and are waiting to be + * read by userspace. + * + * All buffers start life on the free list, then move successively to the + * inflight pointer, and then to the used list. After they have been read by + * userspace, they are moved back to the free list. The cycle repeats as long + * as necessary. + * + * It should be noted that all buffers are mapped and ready for DMA when they + * are on any of the three lists. They are only unmapped when they are in the + * process of being read by userspace. + */ + +/* + * Notes on the IRQ masking scheme: + * + * The IRQ masking scheme here is different than most other hardware. The only + * way for the DATA-FPGAs to detect if the kernel has taken too long to copy + * the data is if the status registers are not cleared before the next + * correlation data dump is ready. + * + * The interrupt line is connected to the status registers, such that when they + * are cleared, the interrupt is de-asserted. Therein lies our problem. We need + * to schedule a long-running DMA operation and return from the interrupt + * handler quickly, but we cannot clear the status registers. + * + * To handle this, the system controller FPGA has the capability to connect the + * interrupt line to a user-controlled GPIO pin. This pin is driven high + * (unasserted) and left that way. To mask the interrupt, we change the + * interrupt source to the GPIO pin. Tada, we hid the interrupt. :) + */ + +#include <linux/of_platform.h> +#include <linux/dma-mapping.h> +#include <linux/miscdevice.h> +#include <linux/interrupt.h> +#include <linux/dmaengine.h> +#include <linux/seq_file.h> +#include <linux/highmem.h> +#include <linux/debugfs.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/poll.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/kref.h> +#include <linux/io.h> + +#include <media/videobuf-dma-sg.h> + +/* system controller registers */ +#define SYS_IRQ_SOURCE_CTL 0x24 +#define SYS_IRQ_OUTPUT_EN 0x28 +#define SYS_IRQ_OUTPUT_DATA 0x2C +#define SYS_IRQ_INPUT_DATA 0x30 +#define SYS_FPGA_CONFIG_STATUS 0x44 + +/* GPIO IRQ line assignment */ +#define IRQ_CORL_DONE 0x10 + +/* FPGA registers */ +#define MMAP_REG_VERSION 0x00 +#define MMAP_REG_CORL_CONF1 0x08 +#define MMAP_REG_CORL_CONF2 0x0C +#define MMAP_REG_STATUS 0x48 + +#define SYS_FPGA_BLOCK 0xF0000000 + +#define DATA_FPGA_START 0x400000 +#define DATA_FPGA_SIZE 0x80000 + +static const char drv_name[] = "carma-fpga"; + +#define NUM_FPGA 4 + +#define MIN_DATA_BUFS 8 +#define MAX_DATA_BUFS 64 + +struct fpga_info { + unsigned int num_lag_ram; + unsigned int blk_size; +}; + +struct data_buf { + struct list_head entry; + struct videobuf_dmabuf vb; + size_t size; +}; + +struct fpga_device { + /* character device */ + struct miscdevice miscdev; + struct device *dev; + struct mutex mutex; + + /* reference count */ + struct kref ref; + + /* FPGA registers and information */ + struct fpga_info info[NUM_FPGA]; + void __iomem *regs; + int irq; + + /* FPGA Physical Address/Size Information */ + resource_size_t phys_addr; + size_t phys_size; + + /* DMA structures */ + struct sg_table corl_table; + unsigned int corl_nents; + struct dma_chan *chan; + + /* Protection for all members below */ + spinlock_t lock; + + /* Device enable/disable flag */ + bool enabled; + + /* Correlation data buffers */ + wait_queue_head_t wait; + struct list_head free; + struct list_head used; + struct data_buf *inflight; + + /* Information about data buffers */ + unsigned int num_dropped; + unsigned int num_buffers; + size_t bufsize; + struct dentry *dbg_entry; +}; + +struct fpga_reader { + struct fpga_device *priv; + struct data_buf *buf; + off_t buf_start; +}; + +static void fpga_device_release(struct kref *ref) +{ + struct fpga_device *priv = container_of(ref, struct fpga_device, ref); + + /* the last reader has exited, cleanup the last bits */ + mutex_destroy(&priv->mutex); + kfree(priv); +} + +/* + * Data Buffer Allocation Helpers + */ + +/** + * data_free_buffer() - free a single data buffer and all allocated memory + * @buf: the buffer to free + * + * This will free all of the pages allocated to the given data buffer, and + * then free the structure itself + */ +static void data_free_buffer(struct data_buf *buf) +{ + /* It is ok to free a NULL buffer */ + if (!buf) + return; + + /* free all memory */ + videobuf_dma_free(&buf->vb); + kfree(buf); +} + +/** + * data_alloc_buffer() - allocate and fill a data buffer with pages + * @bytes: the number of bytes required + * + * This allocates all space needed for a data buffer. It must be mapped before + * use in a DMA transaction using videobuf_dma_map(). + * + * Returns NULL on failure + */ +static struct data_buf *data_alloc_buffer(const size_t bytes) +{ + unsigned int nr_pages; + struct data_buf *buf; + int ret; + + /* calculate the number of pages necessary */ + nr_pages = DIV_ROUND_UP(bytes, PAGE_SIZE); + + /* allocate the buffer structure */ + buf = kzalloc(sizeof(*buf), GFP_KERNEL); + if (!buf) + goto out_return; + + /* initialize internal fields */ + INIT_LIST_HEAD(&buf->entry); + buf->size = bytes; + + /* allocate the videobuf */ + videobuf_dma_init(&buf->vb); + ret = videobuf_dma_init_kernel(&buf->vb, DMA_FROM_DEVICE, nr_pages); + if (ret) + goto out_free_buf; + + return buf; + +out_free_buf: + kfree(buf); +out_return: + return NULL; +} + +/** + * data_free_buffers() - free all allocated buffers + * @priv: the driver's private data structure + * + * Free all buffers allocated by the driver (except those currently in the + * process of being read by userspace). + * + * LOCKING: must hold dev->mutex + * CONTEXT: user + */ +static void data_free_buffers(struct fpga_device *priv) +{ + struct data_buf *buf, *tmp; + + /* the device should be stopped, no DMA in progress */ + BUG_ON(priv->inflight != NULL); + + list_for_each_entry_safe(buf, tmp, &priv->free, entry) { + list_del_init(&buf->entry); + videobuf_dma_unmap(priv->dev, &buf->vb); + data_free_buffer(buf); + } + + list_for_each_entry_safe(buf, tmp, &priv->used, entry) { + list_del_init(&buf->entry); + videobuf_dma_unmap(priv->dev, &buf->vb); + data_free_buffer(buf); + } + + priv->num_buffers = 0; + priv->bufsize = 0; +} + +/** + * data_alloc_buffers() - allocate 1 seconds worth of data buffers + * @priv: the driver's private data structure + * + * Allocate enough buffers for a whole second worth of data + * + * This routine will attempt to degrade nicely by succeeding even if a full + * second worth of data buffers could not be allocated, as long as a minimum + * number were allocated. In this case, it will print a message to the kernel + * log. + * + * The device must not be modifying any lists when this is called. + * + * CONTEXT: user + * LOCKING: must hold dev->mutex + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_alloc_buffers(struct fpga_device *priv) +{ + struct data_buf *buf; + int i, ret; + + for (i = 0; i < MAX_DATA_BUFS; i++) { + + /* allocate a buffer */ + buf = data_alloc_buffer(priv->bufsize); + if (!buf) + break; + + /* map it for DMA */ + ret = videobuf_dma_map(priv->dev, &buf->vb); + if (ret) { + data_free_buffer(buf); + break; + } + + /* add it to the list of free buffers */ + list_add_tail(&buf->entry, &priv->free); + priv->num_buffers++; + } + + /* Make sure we allocated the minimum required number of buffers */ + if (priv->num_buffers < MIN_DATA_BUFS) { + dev_err(priv->dev, "Unable to allocate enough data buffers\n"); + data_free_buffers(priv); + return -ENOMEM; + } + + /* Warn if we are running in a degraded state, but do not fail */ + if (priv->num_buffers < MAX_DATA_BUFS) { + dev_warn(priv->dev, + "Unable to allocate %d buffers, using %d buffers instead\n", + MAX_DATA_BUFS, i); + } + + return 0; +} + +/* + * DMA Operations Helpers + */ + +/** + * fpga_start_addr() - get the physical address a DATA-FPGA + * @priv: the driver's private data structure + * @fpga: the DATA-FPGA number (zero based) + */ +static dma_addr_t fpga_start_addr(struct fpga_device *priv, unsigned int fpga) +{ + return priv->phys_addr + 0x400000 + (0x80000 * fpga); +} + +/** + * fpga_block_addr() - get the physical address of a correlation data block + * @priv: the driver's private data structure + * @fpga: the DATA-FPGA number (zero based) + * @blknum: the correlation block number (zero based) + */ +static dma_addr_t fpga_block_addr(struct fpga_device *priv, unsigned int fpga, + unsigned int blknum) +{ + return fpga_start_addr(priv, fpga) + (0x10000 * (1 + blknum)); +} + +#define REG_BLOCK_SIZE (32 * 4) + +/** + * data_setup_corl_table() - create the scatterlist for correlation dumps + * @priv: the driver's private data structure + * + * Create the scatterlist for transferring a correlation dump from the + * DATA FPGAs. This structure will be reused for each buffer than needs + * to be filled with correlation data. + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_setup_corl_table(struct fpga_device *priv) +{ + struct sg_table *table = &priv->corl_table; + struct scatterlist *sg; + struct fpga_info *info; + int i, j, ret; + + /* Calculate the number of entries needed */ + priv->corl_nents = (1 + NUM_FPGA) * REG_BLOCK_SIZE; + for (i = 0; i < NUM_FPGA; i++) + priv->corl_nents += priv->info[i].num_lag_ram; + + /* Allocate the scatterlist table */ + ret = sg_alloc_table(table, priv->corl_nents, GFP_KERNEL); + if (ret) { + dev_err(priv->dev, "unable to allocate DMA table\n"); + return ret; + } + + /* Add the DATA FPGA registers to the scatterlist */ + sg = table->sgl; + for (i = 0; i < NUM_FPGA; i++) { + sg_dma_address(sg) = fpga_start_addr(priv, i); + sg_dma_len(sg) = REG_BLOCK_SIZE; + sg = sg_next(sg); + } + + /* Add the SYS-FPGA registers to the scatterlist */ + sg_dma_address(sg) = SYS_FPGA_BLOCK; + sg_dma_len(sg) = REG_BLOCK_SIZE; + sg = sg_next(sg); + + /* Add the FPGA correlation data blocks to the scatterlist */ + for (i = 0; i < NUM_FPGA; i++) { + info = &priv->info[i]; + for (j = 0; j < info->num_lag_ram; j++) { + sg_dma_address(sg) = fpga_block_addr(priv, i, j); + sg_dma_len(sg) = info->blk_size; + sg = sg_next(sg); + } + } + + /* + * All physical addresses and lengths are present in the structure + * now. It can be reused for every FPGA DATA interrupt + */ + return 0; +} + +/* + * FPGA Register Access Helpers + */ + +static void fpga_write_reg(struct fpga_device *priv, unsigned int fpga, + unsigned int reg, u32 val) +{ + const int fpga_start = DATA_FPGA_START + (fpga * DATA_FPGA_SIZE); + iowrite32be(val, priv->regs + fpga_start + reg); +} + +static u32 fpga_read_reg(struct fpga_device *priv, unsigned int fpga, + unsigned int reg) +{ + const int fpga_start = DATA_FPGA_START + (fpga * DATA_FPGA_SIZE); + return ioread32be(priv->regs + fpga_start + reg); +} + +/** + * data_calculate_bufsize() - calculate the data buffer size required + * @priv: the driver's private data structure + * + * Calculate the total buffer size needed to hold a single block + * of correlation data + * + * CONTEXT: user + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_calculate_bufsize(struct fpga_device *priv) +{ + u32 num_corl, num_lags, num_meta, num_qcnt, num_pack; + u32 conf1, conf2, version; + u32 num_lag_ram, blk_size; + int i; + + /* Each buffer starts with the 5 FPGA register areas */ + priv->bufsize = (1 + NUM_FPGA) * REG_BLOCK_SIZE; + + /* Read and store the configuration data for each FPGA */ + for (i = 0; i < NUM_FPGA; i++) { + version = fpga_read_reg(priv, i, MMAP_REG_VERSION); + conf1 = fpga_read_reg(priv, i, MMAP_REG_CORL_CONF1); + conf2 = fpga_read_reg(priv, i, MMAP_REG_CORL_CONF2); + + /* minor version 2 and later */ + if ((version & 0x000000FF) >= 2) { + num_corl = (conf1 & 0x000000F0) >> 4; + num_pack = (conf1 & 0x00000F00) >> 8; + num_lags = (conf1 & 0x00FFF000) >> 12; + num_meta = (conf1 & 0x7F000000) >> 24; + num_qcnt = (conf2 & 0x00000FFF) >> 0; + } else { + num_corl = (conf1 & 0x000000F0) >> 4; + num_pack = 1; /* implied */ + num_lags = (conf1 & 0x000FFF00) >> 8; + num_meta = (conf1 & 0x7FF00000) >> 20; + num_qcnt = (conf2 & 0x00000FFF) >> 0; + } + + num_lag_ram = (num_corl + num_pack - 1) / num_pack; + blk_size = ((num_pack * num_lags) + num_meta + num_qcnt) * 8; + + priv->info[i].num_lag_ram = num_lag_ram; + priv->info[i].blk_size = blk_size; + priv->bufsize += num_lag_ram * blk_size; + + dev_dbg(priv->dev, "FPGA %d NUM_CORL: %d\n", i, num_corl); + dev_dbg(priv->dev, "FPGA %d NUM_PACK: %d\n", i, num_pack); + dev_dbg(priv->dev, "FPGA %d NUM_LAGS: %d\n", i, num_lags); + dev_dbg(priv->dev, "FPGA %d NUM_META: %d\n", i, num_meta); + dev_dbg(priv->dev, "FPGA %d NUM_QCNT: %d\n", i, num_qcnt); + dev_dbg(priv->dev, "FPGA %d BLK_SIZE: %d\n", i, blk_size); + } + + dev_dbg(priv->dev, "TOTAL BUFFER SIZE: %zu bytes\n", priv->bufsize); + return 0; +} + +/* + * Interrupt Handling + */ + +/** + * data_disable_interrupts() - stop the device from generating interrupts + * @priv: the driver's private data structure + * + * Hide interrupts by switching to GPIO interrupt source + * + * LOCKING: must hold dev->lock + */ +static void data_disable_interrupts(struct fpga_device *priv) +{ + /* hide the interrupt by switching the IRQ driver to GPIO */ + iowrite32be(0x2F, priv->regs + SYS_IRQ_SOURCE_CTL); +} + +/** + * data_enable_interrupts() - allow the device to generate interrupts + * @priv: the driver's private data structure + * + * Unhide interrupts by switching to the FPGA interrupt source. At the + * same time, clear the DATA-FPGA status registers. + * + * LOCKING: must hold dev->lock + */ +static void data_enable_interrupts(struct fpga_device *priv) +{ + /* clear the actual FPGA corl_done interrupt */ + fpga_write_reg(priv, 0, MMAP_REG_STATUS, 0x0); + fpga_write_reg(priv, 1, MMAP_REG_STATUS, 0x0); + fpga_write_reg(priv, 2, MMAP_REG_STATUS, 0x0); + fpga_write_reg(priv, 3, MMAP_REG_STATUS, 0x0); + + /* flush the writes */ + fpga_read_reg(priv, 0, MMAP_REG_STATUS); + + /* switch back to the external interrupt source */ + iowrite32be(0x3F, priv->regs + SYS_IRQ_SOURCE_CTL); +} + +/** + * data_dma_cb() - DMAEngine callback for DMA completion + * @data: the driver's private data structure + * + * Complete a DMA transfer from the DATA-FPGA's + * + * This is called via the DMA callback mechanism, and will handle moving the + * completed DMA transaction to the used list, and then wake any processes + * waiting for new data + * + * CONTEXT: any, softirq expected + */ +static void data_dma_cb(void *data) +{ + struct fpga_device *priv = data; + unsigned long flags; + + spin_lock_irqsave(&priv->lock, flags); + + /* If there is no inflight buffer, we've got a bug */ + BUG_ON(priv->inflight == NULL); + + /* Move the inflight buffer onto the used list */ + list_move_tail(&priv->inflight->entry, &priv->used); + priv->inflight = NULL; + + /* clear the FPGA status and re-enable interrupts */ + data_enable_interrupts(priv); + + spin_unlock_irqrestore(&priv->lock, flags); + + /* + * We've changed both the inflight and used lists, so we need + * to wake up any processes that are blocking for those events + */ + wake_up(&priv->wait); +} + +/** + * data_submit_dma() - prepare and submit the required DMA to fill a buffer + * @priv: the driver's private data structure + * @buf: the data buffer + * + * Prepare and submit the necessary DMA transactions to fill a correlation + * data buffer. + * + * LOCKING: must hold dev->lock + * CONTEXT: hardirq only + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_submit_dma(struct fpga_device *priv, struct data_buf *buf) +{ + struct scatterlist *dst_sg, *src_sg; + unsigned int dst_nents, src_nents; + struct dma_chan *chan = priv->chan; + struct dma_async_tx_descriptor *tx; + dma_cookie_t cookie; + dma_addr_t dst, src; + + dst_sg = buf->vb.sglist; + dst_nents = buf->vb.sglen; + + src_sg = priv->corl_table.sgl; + src_nents = priv->corl_nents; + + /* + * All buffers passed to this function should be ready and mapped + * for DMA already. Therefore, we don't need to do anything except + * submit it to the Freescale DMA Engine for processing + */ + + /* setup the scatterlist to scatterlist transfer */ + tx = chan->device->device_prep_dma_sg(chan, + dst_sg, dst_nents, + src_sg, src_nents, + 0); + if (!tx) { + dev_err(priv->dev, "unable to prep scatterlist DMA\n"); + return -ENOMEM; + } + + /* submit the transaction to the DMA controller */ + cookie = tx->tx_submit(tx); + if (dma_submit_error(cookie)) { + dev_err(priv->dev, "unable to submit scatterlist DMA\n"); + return -ENOMEM; + } + + /* Prepare the re-read of the SYS-FPGA block */ + dst = sg_dma_address(dst_sg) + (NUM_FPGA * REG_BLOCK_SIZE); + src = SYS_FPGA_BLOCK; + tx = chan->device->device_prep_dma_memcpy(chan, dst, src, + REG_BLOCK_SIZE, + DMA_PREP_INTERRUPT); + if (!tx) { + dev_err(priv->dev, "unable to prep SYS-FPGA DMA\n"); + return -ENOMEM; + } + + /* Setup the callback */ + tx->callback = data_dma_cb; + tx->callback_param = priv; + + /* submit the transaction to the DMA controller */ + cookie = tx->tx_submit(tx); + if (dma_submit_error(cookie)) { + dev_err(priv->dev, "unable to submit SYS-FPGA DMA\n"); + return -ENOMEM; + } + + return 0; +} + +#define CORL_DONE 0x1 +#define CORL_ERR 0x2 + +static irqreturn_t data_irq(int irq, void *dev_id) +{ + struct fpga_device *priv = dev_id; + bool submitted = false; + struct data_buf *buf; + u32 status; + int i; + + /* detect spurious interrupts via FPGA status */ + for (i = 0; i < 4; i++) { + status = fpga_read_reg(priv, i, MMAP_REG_STATUS); + if (!(status & (CORL_DONE | CORL_ERR))) { + dev_err(priv->dev, "spurious irq detected (FPGA)\n"); + return IRQ_NONE; + } + } + + /* detect spurious interrupts via raw IRQ pin readback */ + status = ioread32be(priv->regs + SYS_IRQ_INPUT_DATA); + if (status & IRQ_CORL_DONE) { + dev_err(priv->dev, "spurious irq detected (IRQ)\n"); + return IRQ_NONE; + } + + spin_lock(&priv->lock); + + /* hide the interrupt by switching the IRQ driver to GPIO */ + data_disable_interrupts(priv); + + /* If there are no free buffers, drop this data */ + if (list_empty(&priv->free)) { + priv->num_dropped++; + goto out; + } + + buf = list_first_entry(&priv->free, struct data_buf, entry); + list_del_init(&buf->entry); + BUG_ON(buf->size != priv->bufsize); + + /* Submit a DMA transfer to get the correlation data */ + if (data_submit_dma(priv, buf)) { + dev_err(priv->dev, "Unable to setup DMA transfer\n"); + list_move_tail(&buf->entry, &priv->free); + goto out; + } + + /* Save the buffer for the DMA callback */ + priv->inflight = buf; + submitted = true; + + /* Start the DMA Engine */ + dma_async_memcpy_issue_pending(priv->chan); + +out: + /* If no DMA was submitted, re-enable interrupts */ + if (!submitted) + data_enable_interrupts(priv); + + spin_unlock(&priv->lock); + return IRQ_HANDLED; +} + +/* + * Realtime Device Enable Helpers + */ + +/** + * data_device_enable() - enable the device for buffered dumping + * @priv: the driver's private data structure + * + * Enable the device for buffered dumping. Allocates buffers and hooks up + * the interrupt handler. When this finishes, data will come pouring in. + * + * LOCKING: must hold dev->mutex + * CONTEXT: user context only + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_device_enable(struct fpga_device *priv) +{ + u32 val; + int ret; + + /* multiple enables are safe: they do nothing */ + if (priv->enabled) + return 0; + + /* check that the FPGAs are programmed */ + val = ioread32be(priv->regs + SYS_FPGA_CONFIG_STATUS); + if (!(val & (1 << 18))) { + dev_err(priv->dev, "DATA-FPGAs are not enabled\n"); + return -ENODATA; + } + + /* read the FPGAs to calculate the buffer size */ + ret = data_calculate_bufsize(priv); + if (ret) { + dev_err(priv->dev, "unable to calculate buffer size\n"); + goto out_error; + } + + /* allocate the correlation data buffers */ + ret = data_alloc_buffers(priv); + if (ret) { + dev_err(priv->dev, "unable to allocate buffers\n"); + goto out_error; + } + + /* setup the source scatterlist for dumping correlation data */ + ret = data_setup_corl_table(priv); + if (ret) { + dev_err(priv->dev, "unable to setup correlation DMA table\n"); + goto out_error; + } + + /* hookup the irq handler */ + ret = request_irq(priv->irq, data_irq, IRQF_SHARED, drv_name, priv); + if (ret) { + dev_err(priv->dev, "unable to request IRQ handler\n"); + goto out_error; + } + + /* switch to the external FPGA IRQ line */ + data_enable_interrupts(priv); + + /* success, we're enabled */ + priv->enabled = true; + return 0; + +out_error: + sg_free_table(&priv->corl_table); + priv->corl_nents = 0; + + data_free_buffers(priv); + return ret; +} + +/** + * data_device_disable() - disable the device for buffered dumping + * @priv: the driver's private data structure + * + * Disable the device for buffered dumping. Stops new DMA transactions from + * being generated, waits for all outstanding DMA to complete, and then frees + * all buffers. + * + * LOCKING: must hold dev->mutex + * CONTEXT: user only + * + * Returns 0 on success, -ERRNO otherwise + */ +static int data_device_disable(struct fpga_device *priv) +{ + int ret; + + /* allow multiple disable */ + if (!priv->enabled) + return 0; + + /* switch to the internal GPIO IRQ line */ + data_disable_interrupts(priv); + + /* unhook the irq handler */ + free_irq(priv->irq, priv); + + /* + * wait for all outstanding DMA to complete + * + * Device interrupts are disabled, therefore another buffer cannot + * be marked inflight. + */ + ret = wait_event_interruptible(priv->wait, priv->inflight == NULL); + if (ret) + return ret; + + /* free the correlation table */ + sg_free_table(&priv->corl_table); + priv->corl_nents = 0; + + /* + * We are taking the spinlock not to protect priv->enabled, but instead + * to make sure that there are no readers in the process of altering + * the free or used lists while we are setting this flag. + */ + spin_lock_irq(&priv->lock); + priv->enabled = false; + spin_unlock_irq(&priv->lock); + + /* free all buffers: the free and used lists are not being changed */ + data_free_buffers(priv); + return 0; +} + +/* + * DEBUGFS Interface + */ +#ifdef CONFIG_DEBUG_FS + +/* + * Count the number of entries in the given list + */ +static unsigned int list_num_entries(struct list_head *list) +{ + struct list_head *entry; + unsigned int ret = 0; + + list_for_each(entry, list) + ret++; + + return ret; +} + +static int data_debug_show(struct seq_file *f, void *offset) +{ + struct fpga_device *priv = f->private; + int ret; + + /* + * Lock the mutex first, so that we get an accurate value for enable + * Lock the spinlock next, to get accurate list counts + */ + ret = mutex_lock_interruptible(&priv->mutex); + if (ret) + return ret; + + spin_lock_irq(&priv->lock); + + seq_printf(f, "enabled: %d\n", priv->enabled); + seq_printf(f, "bufsize: %d\n", priv->bufsize); + seq_printf(f, "num_buffers: %d\n", priv->num_buffers); + seq_printf(f, "num_free: %d\n", list_num_entries(&priv->free)); + seq_printf(f, "inflight: %d\n", priv->inflight != NULL); + seq_printf(f, "num_used: %d\n", list_num_entries(&priv->used)); + seq_printf(f, "num_dropped: %d\n", priv->num_dropped); + + spin_unlock_irq(&priv->lock); + mutex_unlock(&priv->mutex); + return 0; +} + +static int data_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, data_debug_show, inode->i_private); +} + +static const struct file_operations data_debug_fops = { + .owner = THIS_MODULE, + .open = data_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int data_debugfs_init(struct fpga_device *priv) +{ + priv->dbg_entry = debugfs_create_file(drv_name, S_IRUGO, NULL, priv, + &data_debug_fops); + if (IS_ERR(priv->dbg_entry)) + return PTR_ERR(priv->dbg_entry); + + return 0; +} + +static void data_debugfs_exit(struct fpga_device *priv) +{ + debugfs_remove(priv->dbg_entry); +} + +#else + +static inline int data_debugfs_init(struct fpga_device *priv) +{ + return 0; +} + +static inline void data_debugfs_exit(struct fpga_device *priv) +{ +} + +#endif /* CONFIG_DEBUG_FS */ + +/* + * SYSFS Attributes + */ + +static ssize_t data_en_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct fpga_device *priv = dev_get_drvdata(dev); + return snprintf(buf, PAGE_SIZE, "%u\n", priv->enabled); +} + +static ssize_t data_en_set(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct fpga_device *priv = dev_get_drvdata(dev); + unsigned long enable; + int ret; + + ret = strict_strtoul(buf, 0, &enable); + if (ret) { + dev_err(priv->dev, "unable to parse enable input\n"); + return -EINVAL; + } + + ret = mutex_lock_interruptible(&priv->mutex); + if (ret) + return ret; + + if (enable) + ret = data_device_enable(priv); + else + ret = data_device_disable(priv); + + if (ret) { + dev_err(priv->dev, "device %s failed\n", + enable ? "enable" : "disable"); + count = ret; + goto out_unlock; + } + +out_unlock: + mutex_unlock(&priv->mutex); + return count; +} + +static DEVICE_ATTR(enable, S_IWUSR | S_IRUGO, data_en_show, data_en_set); + +static struct attribute *data_sysfs_attrs[] = { + &dev_attr_enable.attr, + NULL, +}; + +static const struct attribute_group rt_sysfs_attr_group = { + .attrs = data_sysfs_attrs, +}; + +/* + * FPGA Realtime Data Character Device + */ + +static int data_open(struct inode *inode, struct file *filp) +{ + /* + * The miscdevice layer puts our struct miscdevice into the + * filp->private_data field. We use this to find our private + * data and then overwrite it with our own private structure. + */ + struct fpga_device *priv = container_of(filp->private_data, + struct fpga_device, miscdev); + struct fpga_reader *reader; + int ret; + + /* allocate private data */ + reader = kzalloc(sizeof(*reader), GFP_KERNEL); + if (!reader) + return -ENOMEM; + + reader->priv = priv; + reader->buf = NULL; + + filp->private_data = reader; + ret = nonseekable_open(inode, filp); + if (ret) { + dev_err(priv->dev, "nonseekable-open failed\n"); + kfree(reader); + return ret; + } + + /* + * success, increase the reference count of the private data structure + * so that it doesn't disappear if the device is unbound + */ + kref_get(&priv->ref); + return 0; +} + +static int data_release(struct inode *inode, struct file *filp) +{ + struct fpga_reader *reader = filp->private_data; + struct fpga_device *priv = reader->priv; + + /* free the per-reader structure */ + data_free_buffer(reader->buf); + kfree(reader); + filp->private_data = NULL; + + /* decrement our reference count to the private data */ + kref_put(&priv->ref, fpga_device_release); + return 0; +} + +static ssize_t data_read(struct file *filp, char __user *ubuf, size_t count, + loff_t *f_pos) +{ + struct fpga_reader *reader = filp->private_data; + struct fpga_device *priv = reader->priv; + struct list_head *used = &priv->used; + struct data_buf *dbuf; + size_t avail; + void *data; + int ret; + + /* check if we already have a partial buffer */ + if (reader->buf) { + dbuf = reader->buf; + goto have_buffer; + } + + spin_lock_irq(&priv->lock); + + /* Block until there is at least one buffer on the used list */ + while (list_empty(used)) { + spin_unlock_irq(&priv->lock); + + if (filp->f_flags & O_NONBLOCK) + return -EAGAIN; + + ret = wait_event_interruptible(priv->wait, !list_empty(used)); + if (ret) + return ret; + + spin_lock_irq(&priv->lock); + } + + /* Grab the first buffer off of the used list */ + dbuf = list_first_entry(used, struct data_buf, entry); + list_del_init(&dbuf->entry); + + spin_unlock_irq(&priv->lock); + + /* Buffers are always mapped: unmap it */ + videobuf_dma_unmap(priv->dev, &dbuf->vb); + + /* save the buffer for later */ + reader->buf = dbuf; + reader->buf_start = 0; + +have_buffer: + /* Get the number of bytes available */ + avail = dbuf->size - reader->buf_start; + data = dbuf->vb.vaddr + reader->buf_start; + + /* Get the number of bytes we can transfer */ + count = min(count, avail); + + /* Copy the data to the userspace buffer */ + if (copy_to_user(ubuf, data, count)) + return -EFAULT; + + /* Update the amount of available space */ + avail -= count; + + /* + * If there is still some data available, save the buffer for the + * next userspace call to read() and return + */ + if (avail > 0) { + reader->buf_start += count; + reader->buf = dbuf; + return count; + } + + /* + * Get the buffer ready to be reused for DMA + * + * If it fails, we pretend that the read never happed and return + * -EFAULT to userspace. The read will be retried. + */ + ret = videobuf_dma_map(priv->dev, &dbuf->vb); + if (ret) { + dev_err(priv->dev, "unable to remap buffer for DMA\n"); + return -EFAULT; + } + + /* Lock against concurrent enable/disable */ + spin_lock_irq(&priv->lock); + + /* the reader is finished with this buffer */ + reader->buf = NULL; + + /* + * One of two things has happened, the device is disabled, or the + * device has been reconfigured underneath us. In either case, we + * should just throw away the buffer. + */ + if (!priv->enabled || dbuf->size != priv->bufsize) { + videobuf_dma_unmap(priv->dev, &dbuf->vb); + data_free_buffer(dbuf); + goto out_unlock; + } + + /* The buffer is safe to reuse, so add it back to the free list */ + list_add_tail(&dbuf->entry, &priv->free); + +out_unlock: + spin_unlock_irq(&priv->lock); + return count; +} + +static unsigned int data_poll(struct file *filp, struct poll_table_struct *tbl) +{ + struct fpga_reader *reader = filp->private_data; + struct fpga_device *priv = reader->priv; + unsigned int mask = 0; + + poll_wait(filp, &priv->wait, tbl); + + if (!list_empty(&priv->used)) + mask |= POLLIN | POLLRDNORM; + + return mask; +} + +static int data_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct fpga_reader *reader = filp->private_data; + struct fpga_device *priv = reader->priv; + unsigned long offset, vsize, psize, addr; + + /* VMA properties */ + offset = vma->vm_pgoff << PAGE_SHIFT; + vsize = vma->vm_end - vma->vm_start; + psize = priv->phys_size - offset; + addr = (priv->phys_addr + offset) >> PAGE_SHIFT; + + /* Check against the FPGA region's physical memory size */ + if (vsize > psize) { + dev_err(priv->dev, "requested mmap mapping too large\n"); + return -EINVAL; + } + + /* IO memory (stop cacheing) */ + vma->vm_flags |= VM_IO | VM_RESERVED; + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + return io_remap_pfn_range(vma, vma->vm_start, addr, vsize, + vma->vm_page_prot); +} + +static const struct file_operations data_fops = { + .owner = THIS_MODULE, + .open = data_open, + .release = data_release, + .read = data_read, + .poll = data_poll, + .mmap = data_mmap, + .llseek = no_llseek, +}; + +/* + * OpenFirmware Device Subsystem + */ + +static bool dma_filter(struct dma_chan *chan, void *data) +{ + /* + * DMA Channel #0 is used for the FPGA Programmer, so ignore it + * + * This probably won't survive an unload/load cycle of the Freescale + * DMAEngine driver, but that won't be a problem + */ + if (chan->chan_id == 0 && chan->device->dev_id == 0) + return false; + + return true; +} + +static int data_of_probe(struct platform_device *op, + const struct of_device_id *match) +{ + struct device_node *of_node = op->dev.of_node; + struct device *this_device; + struct fpga_device *priv; + struct resource res; + dma_cap_mask_t mask; + int ret; + + /* Allocate private data */ + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { + dev_err(&op->dev, "Unable to allocate device private data\n"); + ret = -ENOMEM; + goto out_return; + } + + dev_set_drvdata(&op->dev, priv); + priv->dev = &op->dev; + kref_init(&priv->ref); + mutex_init(&priv->mutex); + + dev_set_drvdata(priv->dev, priv); + spin_lock_init(&priv->lock); + INIT_LIST_HEAD(&priv->free); + INIT_LIST_HEAD(&priv->used); + init_waitqueue_head(&priv->wait); + + /* Setup the misc device */ + priv->miscdev.minor = MISC_DYNAMIC_MINOR; + priv->miscdev.name = drv_name; + priv->miscdev.fops = &data_fops; + + /* Get the physical address of the FPGA registers */ + ret = of_address_to_resource(of_node, 0, &res); + if (ret) { + dev_err(&op->dev, "Unable to find FPGA physical address\n"); + ret = -ENODEV; + goto out_free_priv; + } + + priv->phys_addr = res.start; + priv->phys_size = resource_size(&res); + + /* ioremap the registers for use */ + priv->regs = of_iomap(of_node, 0); + if (!priv->regs) { + dev_err(&op->dev, "Unable to ioremap registers\n"); + ret = -ENOMEM; + goto out_free_priv; + } + + dma_cap_zero(mask); + dma_cap_set(DMA_MEMCPY, mask); + dma_cap_set(DMA_INTERRUPT, mask); + dma_cap_set(DMA_SLAVE, mask); + dma_cap_set(DMA_SG, mask); + + /* Request a DMA channel */ + priv->chan = dma_request_channel(mask, dma_filter, NULL); + if (!priv->chan) { + dev_err(&op->dev, "Unable to request DMA channel\n"); + ret = -ENODEV; + goto out_unmap_regs; + } + + /* Find the correct IRQ number */ + priv->irq = irq_of_parse_and_map(of_node, 0); + if (priv->irq == NO_IRQ) { + dev_err(&op->dev, "Unable to find IRQ line\n"); + ret = -ENODEV; + goto out_release_dma; + } + + /* Drive the GPIO for FPGA IRQ high (no interrupt) */ + iowrite32be(IRQ_CORL_DONE, priv->regs + SYS_IRQ_OUTPUT_DATA); + + /* Register the miscdevice */ + ret = misc_register(&priv->miscdev); + if (ret) { + dev_err(&op->dev, "Unable to register miscdevice\n"); + goto out_irq_dispose_mapping; + } + + /* Create the debugfs files */ + ret = data_debugfs_init(priv); + if (ret) { + dev_err(&op->dev, "Unable to create debugfs files\n"); + goto out_misc_deregister; + } + + /* Create the sysfs files */ + this_device = priv->miscdev.this_device; + dev_set_drvdata(this_device, priv); + ret = sysfs_create_group(&this_device->kobj, &rt_sysfs_attr_group); + if (ret) { + dev_err(&op->dev, "Unable to create sysfs files\n"); + goto out_data_debugfs_exit; + } + + dev_info(&op->dev, "CARMA FPGA Realtime Data Driver Loaded\n"); + return 0; + +out_data_debugfs_exit: + data_debugfs_exit(priv); +out_misc_deregister: + misc_deregister(&priv->miscdev); +out_irq_dispose_mapping: + irq_dispose_mapping(priv->irq); +out_release_dma: + dma_release_channel(priv->chan); +out_unmap_regs: + iounmap(priv->regs); +out_free_priv: + kref_put(&priv->ref, fpga_device_release); +out_return: + return ret; +} + +static int data_of_remove(struct platform_device *op) +{ + struct fpga_device *priv = dev_get_drvdata(&op->dev); + struct device *this_device = priv->miscdev.this_device; + + /* remove all sysfs files, now the device cannot be re-enabled */ + sysfs_remove_group(&this_device->kobj, &rt_sysfs_attr_group); + + /* remove all debugfs files */ + data_debugfs_exit(priv); + + /* disable the device from generating data */ + data_device_disable(priv); + + /* remove the character device to stop new readers from appearing */ + misc_deregister(&priv->miscdev); + + /* cleanup everything not needed by readers */ + irq_dispose_mapping(priv->irq); + dma_release_channel(priv->chan); + iounmap(priv->regs); + + /* release our reference */ + kref_put(&priv->ref, fpga_device_release); + return 0; +} + +static struct of_device_id data_of_match[] = { + { .compatible = "carma,carma-fpga", }, + {}, +}; + +static struct of_platform_driver data_of_driver = { + .probe = data_of_probe, + .remove = data_of_remove, + .driver = { + .name = drv_name, + .of_match_table = data_of_match, + .owner = THIS_MODULE, + }, +}; + +/* + * Module Init / Exit + */ + +static int __init data_init(void) +{ + return of_register_platform_driver(&data_of_driver); +} + +static void __exit data_exit(void) +{ + of_unregister_platform_driver(&data_of_driver); +} + +MODULE_AUTHOR("Ira W. Snyder <iws@ovro.caltech.edu>"); +MODULE_DESCRIPTION("CARMA DATA-FPGA Access Driver"); +MODULE_LICENSE("GPL"); + +module_init(data_init); +module_exit(data_exit); |